Commercial detection with silences

From MythTV Official Wiki
Revision as of 20:41, 20 March 2013 by Dizygotheca (Talk | contribs)

Jump to: navigation, search

Author Hippo
Description A python program based on Mythcommflag-wrapper (thank you Cowbut) that can be used on UK FreeviewHD channels and probably others.
Supports Version25.png  Version26.png 


Original version

I tried out the scripts in Mythcommflag-wrapper and they worked well on the Freeview channels I receive but not on the FreeviewHD channels. The reason is that the audio on FreevieHD is an AAC stream and not an MP3 stream. Fixing that would require decoding from AAC and encoding back to MP3 before letting the script analyse the MP3 stream. So I wrote a little C program to analyze an uncompressed audio stream and a Python program to wrap it up and turn the output into a commercial skip list.

To use this

  • Compile the two C programs and put them somewhere the Python program can find it. (e.g. /usr/local/bin)
  • Copy the Python program to somehwere the backend can find it.
  • Follow the instructions on Mythcommflag-wrapper except the job setting should be 'mausc-wrapper.py %JOBID%'

The python program uses avconv to decode the program file to an AU stream. If you don't have avconv replace it with ffmpeg or mythffmpeg (avconv is the new name for ffmpeg). It upconverts the audio to 6 channels so that it works even when the audio switches around. If you know you only ever get stereo you can replace the 6 with 2 to save a bit of CPU power. It might have to go up in future. Up-converting is better because it's low power and always works whereas down-converting may fail depending on your version of avconv/ffmpeg.

This can do near-realtime commflagging by enabling the backend setting to start commflagging when the recording starts. (mythtv-setup/General/Page9-JobQueueGlobal). The programs mark entries in the cutlist <max-break-setting> after the start of a break is detected so this will be after the commercial break has ended. If you are displaying the programme and get too close to the end you will be in the commercials before they are flagged. C'est la vie.

It's low CPU in that it only decodes the audio stream and since it follows the end of the recording it shouldn't thrash the memory or disk. avconv takes about 2% to decode ITV1-HD on a 1.6GHz Atom Asus motherboard. catagrower takes about 1% and could be a lot better if made less portable.

Script.png catagrower.c

/* Copyright 2012 Crackers Phipps. */
/* Public domain. */
/* Compile with
   gcc -std=c99 -O catagrower.c -o catagrower
*/
/* This program will stop when the file has not grown for this many seconds. */
#define TIMEOUT 60

/* MythTV files are often large. */
#define _FILE_OFFSET_BITS 64

#include <stdio.h>
#include <stdlib.h>
#include <fcntl.h>
#include <unistd.h>

static void usage(const char *name) {
  fprintf(stderr, "Usage: %s <file>\n", name);
  fprintf(stderr, "<file>: file to be monitored.\n");
  fprintf(stderr, "The contents of the file will be copied to stdout.\n");
  fprintf(stderr, "Copying will stop when the file has stopped growing.\n");
}

int main(int argc, char **argv) {

  /* Check usage. */
  if (2 != argc) {
    usage(argv[0]);
    exit(1);
  }

  /* Load options. */
  int fd;
  if (-1 == (fd = open(argv[1], O_RDONLY))) {
    fprintf(stderr, "Could not open %s for reading.\n", argv[1]);
    usage(argv[0]);
    exit(2);
  }

#define BUFFSIZE 4096
  int timer = TIMEOUT;
  char buffer[BUFFSIZE];
  int bytes;
  while (timer > 0) {
    while (0 != (bytes = read(fd, buffer, BUFFSIZE))) {
      write (STDOUT_FILENO, buffer, bytes);
      timer = TIMEOUT;
    }
    sleep(1);
    timer--;
  }
  return 0;
}


Script.png mausc.c

/* Copyright 2013 Tinsel Phipps. */
/* Public domain. Links with libsndfile which is GPL. */
/* Compile with
   gcc -std=c99 -O mausc.c -o mausc -lsndfile -lm
   You may need the libsndfile-dev package installed.
*/
#include <stdlib.h>
#include <math.h>
#include <sndfile.h>
#include <errno.h>
#include <unistd.h>
#include <limits.h>

static void usage(const char *name) {
  fprintf(stderr, "Usage: %s <threshold> <min> <max> <rate>\n", name);
  fprintf(stderr, "<threshold>: silence threshold in dB.\n");
  fprintf(stderr, "<min>: minimum time for silence detection in seconds.\n");
  fprintf(stderr, "<max>: maximum length of breaks in seconds.\n");
  fprintf(stderr, "<rate>: frame rate of video.\n");
  fprintf(stderr, "An AU format file should be fed into this program.\n");
  fprintf(stderr, "Example: %s -70 0.15 400 25 < audio.au\n", name);
}

int main(int argc, char **argv) {

  /* Check usage. */
  if (5 != argc) {
    usage(argv[0]);
    exit(1);
  }

  /* Load options. */
  float threshold, min, max, rate;
  if (1 != sscanf(argv[1], "%f", &threshold)) {
    fprintf(stderr, "Could not parse threshold option into a number.\n");
    usage(argv[0]);
    exit(2);
  }
  if (1 != sscanf(argv[2], "%f", &min)) {
    fprintf(stderr, "Could not parse min option into a number.\n");
    usage(argv[0]);
    exit(2);
  }
  if (1 != sscanf(argv[3], "%f", &max)) {
    fprintf(stderr, "Could not parse max option into a number.\n");
    usage(argv[0]);
    exit(2);
  }
  if (1 != sscanf(argv[4], "%f", &rate)) {
    fprintf(stderr, "Could not parse rate option into a number.\n");
    usage(argv[0]);
    exit(2);
  }

  /* Scale threshold to integer range that libsndfile will use. */
  threshold = INT_MAX * pow(10, threshold / 20);
  /* Scale times to frames. */
  min = min * rate;
  max = max * rate;

  /* Check the input is an audiofile. */
  SNDFILE *input;
  SF_INFO metadata;
  input = sf_open_fd(STDIN_FILENO, SFM_READ, &metadata, SF_FALSE);
  if (NULL == input) {
    sf_perror(NULL);
    return sf_error(NULL);
  }

  /* Allocate data buffer to contain audio data from one video frame. */
  size_t frameSamples = metadata.channels * metadata.samplerate / rate;

  int *samples;
  samples = malloc(frameSamples * sizeof(int));
  if (NULL == samples) {
    perror(NULL);
    return errno;
  }

  /* Process the file one frame at a time and process cuts along the way. */
  int frames = 0;
  int silent = 0;
  int last_silent = 0;
  int gapend = 0;
  int gapstart = 0;
  int first_gapstart = 0;
  while (frameSamples == sf_read_int(input, samples, frameSamples)) {
    frames++;
    int maxabs = 0;
    for (unsigned i = 0; i < frameSamples; i++) {
      samples[i] = abs(samples[i]);
      maxabs = (maxabs > samples[i]) ? maxabs : samples[i];
    }
    last_silent = silent;
    silent = (maxabs < threshold);
    /* Remember first transition to silence. */
    if (silent && !gapstart) {
      gapstart = frames;
    }
    /* Store last transition out of silence. */
    if (!silent && last_silent) {
      /* Make sure it is long enough. */
      if (frames > gapstart + min) {
        gapend = frames;
        if (!first_gapstart) {
          first_gapstart = gapstart;
        }
      }
      gapstart = 0;
    }
    /* Create a skip when max frames have passed. */
    if (first_gapstart && gapend && frames > first_gapstart + max) {
      printf("%d %d\n", first_gapstart, gapend);
      fflush(stdout);
      gapstart = 0;
      gapend = 0;
      first_gapstart = 0;
    }
  }
  /* At end of file can have an unprocessed gap. */
  if (first_gapstart) {
    if (first_gapstart == gapstart) {
      gapend = frames;
    }
    printf("%d %d\n", first_gapstart, gapend);
  }
  return sf_close(input);
}


Script.png mausc-wrapper

#!/usr/bin/env python
# Build a skiplist from silence in the audio track.
# Based on http://www.mythtv.org/wiki/Transcode_wrapper_stub
from MythTV import MythDB, Job, Recorded, findfile, MythLog
from os import path
from subprocess import Popen, PIPE
from optparse import OptionParser

def runjob(jobid=None, chanid=None, starttime=None):
    # Tunable settings (would like to retrieve per channel from the database)
    thresh = -70 # Silence threshold in dB.
    minquiet = 0.15 # Minimum time for silence detection in seconds.
    maxbreak = 400 # Maximum length of adverts breaks.
    rate = 25 # Frame rate of video. (should be automatic)

    db = MythDB()
    if jobid:
        job = Job(jobid, db=db)
        chanid = job.chanid
        starttime = job.starttime

    try:
        rec = Recorded((chanid, starttime), db=db)
    except:
        if jobid:
            job.update({'status':job.ERRORED,
                        'comment':'ERROR: Could not find recording.'})
        else:
            print 'Could not find recording.'
        exit(1)

    # Get program handle in standard format.
    starttime = rec.starttime
    chanid = rec.chanid

    sg = findfile(rec.basename, rec.storagegroup, db=db)
    if sg is None:
        if jobid:
            job.update({'status':job.ERRORED,
                        'comment':'ERROR: Local access to recording not found.'})
        else:
            print 'Local access to recording not found.'
        exit(1)

    infile = path.join(sg.dirname, rec.basename)

    # Purge any existing skip list.
    rec.markup.clean()
    rec.commflagged = 0
    rec.update()

    # Write out the file contents and keep going till recording is finished.
    p1 = Popen(["catagrower", infile],
               stdout = PIPE)
    # Pipe through avconv to extract uncompressed audio stream.
    p2 = Popen(["avconv", "-v", "8", "-i", "pipe:0", "-f", "au", "-ac", "6", "-"],
               stdin = p1.stdout, stdout = PIPE)
    # Pipe to mausc which will spit out a list of breaks.
    p3 = Popen(["mausc", str(thresh), str(minquiet), str(maxbreak), str(rate)],
               stdin = p2.stdout, stdout = PIPE)

    # Store breaks in the database.
    breaks = 0
    while 1:
        line = p3.stdout.readline()
        if not line:
            break
        start, end = line.split()
        rec.markup.append(start, rec.markup.MARK_COMM_START, None)
        rec.markup.append(end, rec.markup.MARK_COMM_END, None)
        rec.commflagged = 1
        rec.update()
        breaks = breaks + 1
        if jobid is None:
            print 'Got a break at frame %s' % start

    if jobid:
        job.update({'status':272,
                    'comment':'Audio commflag detected %s breaks.' % breaks
                    })
    else:
        print 'Audio commflag detected %s breaks.' % breaks

def main():
    parser = OptionParser(usage="usage: %prog [options] [jobid]")

    parser.add_option('--chanid', action='store', type='int',
                      dest='chanid', help='Use chanid for manual operation')
    parser.add_option('--starttime', action='store', type='string',
                      dest='stime', help='Use starttime for manual operation')
    MythLog.loadOptParse(parser)
    opts, args = parser.parse_args()

    if len(args) == 1:
        runjob(jobid=args[0])
    elif opts.chanid and opts.stime:
        runjob(chanid=opts.chanid, starttime=opts.stime)
    else:
        print 'Script must be provided either jobid, or chanid and starttime.'
        parser.print_help()
        exit(1)

if __name__ == '__main__':
    main()

Cluster Detecting Version

The basic silence detection algorithm is easily thrown by odd silences that occur within 6 mins of an advert and performs poorly on animations/kids programmes. I was keen to cut adverts out of my kids' shows so I developed an algorithm that detects clusters of silences: adverts are characterised by many silences close together whilst isolated silences within programmes are ignored.

Hippo has provided a good platform for a commflagging script. New features of this version are;

  • Determine ad breaks from clusters of silences. Solves those occasional glitches caused by silences within programmes and does a pretty good job on animations/kids programmes. Also allows the silence detection to be more sensitive (to pick up short and/or long silences) as rogue ones will be ignored.
  • Integrates the script with Myth logging. Works well with rsyslog (Mythbuntu). Should also work with file logging but I haven't tested it.
  • Allows parameters to be varied per-channel and per-programme. Useful for channels with 'noisier' ad breaks, ie. Dave, and regular programmes where the defaults don't suit you.
  • Sends ad breaks to mythplayer as they are found. If you start watching a prog before it has finished recording then the comm-skipping will still work (assuming you're not too close to real-time).

Algorithm

An advert is defined as a cluster of silences, at least <minbreak> long, that is composed of at least <mindetect> silences that occur within <maxsep> of each other.

In practice, silences are detected as a consecutive series of frames having an average audio power below <threshold> for at least <minquiet>. If the interval between a silence and the previous one is less than <maxsep> then they belong to the same cluster; otherwise they lie in different clusters. Clusters that are shorter than <minbreak> or composed of less than <mindetect> silences are ignored. Adverts are shortened by <padding> on both sides.

Although adverts are reported in real-time, all silences and clusters are stored - I originally envisaged using post-scan analysis to amend the detected adverts. However, so far, this hasn't proved necessary or viable.

Change Summary

  • catagrower.cpp has minor mods to take its timeout from an arg. This is to allow the script to be run manually from the command line.
  • silence.cpp replaces mausc.c. New algorithm. Optionally uses Qt/Myth libs in order to send messages to mythplayer.
  • silence.py replaces mausc-wrapper.py. I've updated the deprecated arg parsing, integrated Myth logging and added channel/prog preset handling. It can reside anywhere but I keep mine in /usr/local/bin. It expects the C++ executables to reside in /usr/local/bin/

Upgrading from previous versions

This version communicates with MythPlayer via the Myth Python bindings. Previous versions communicated directly which (optionally) needed Myth & Qt header files to be installed. If you installed libmyth-dev & libqt4-dev just for this reason then they are no longer needed. However be wary of simply uninstalling them - that may break Myth as they also contain libraries. To remove them correctly you will probably have to reinstall Qt & Myth afterwards. It's safer to leave them installed.

Requirements

  • Compilation environment (gcc, make) - install package build-essential
  • libsndfile for reading audio samples - install package libsndfile-dev
  • Python 2.7 for the new argument parser

Building

  • Copy catagrower.cpp, silence.cpp, silence.py & Makefile to a new directory and cd there.
  • Build the silence & catagrower executables using "make"
  • Install executables & Python script to /usr/local/bin/ using "sudo make install".
  • The Makefile works for me using gcc 4.6.3 (Ubuntu 12.04) & Myth 0.26. I'm no expert on C++ standards so earlier versions may need some tinkering.

Notes

  • I only use Freeview SD, so I downmix my stereo reception to 1 channel to improve performance. Refer to Hippo's comments above regarding the number of channels and update silence.py (kUpmix_Channels) accordingly.
  • I also reduce the audio sample rate (silence.py line 176, "-ar 8000") to reduce the data throughput. Ultimately all channels/samples are reduced to a single audio power per frame and I haven't noticed any qualitative difference from this optimisation. However it could affect the mythffmpeg load; if loading/performance is important to you, you may wish to experiment with this.
  • silence.py uses mythffmpeg but, as Hippo states, you can simply replace with avconv/ffmpeg. I notice no difference.
  • <minbreak> and <mindetect> do not apply to pre-roll/post-roll (starting/ending) 'adverts'.
  • Mythplayer will not auto-skip pre-roll/post-roll breaks. When starting playback you need to manually comm-skip to the programme start.
  • The log information can be initially confusing - bear in mind the algorithmic process when interpreting it. The interval of a silence always relates to the previous silence; the interval reported by a cluster always relates to the previous cluster. Silences report their audio power whereas clusters report the number of silences they contain.
  • If processing manually, note that silence.py clears any existing comm-skip list on startup. Be aware that this also appears to erase the bookmark (and maybe other mark-ups).
  • UK commercials are usually 10-60 secs long. However I have seen occasional film trailers that are 2 min long (of constant noise). Thus <maxsep> defaults to 120. If you don't mind the odd trailer then reducing <maxsep> to 60 or 90 would probably reduce erroneous cuts.

Running

Assuming you use the same locations, your 'Advert-detection command' (mythtv-setup/General/Page 8) should be:

 /usr/local/bin/silence.py %JOBID% %VERBOSEMODE% --loglevel debug

You can also run it manually from the command line like this:

 silence.py --chanid 1004 --starttime 20130117220000 --loglevel debug

INFO logging shows details of the clusters/cuts, DEBUG logging also shows details of the detected silences.

My performance of SD content on an ageing ASUS M2NPV-VM/Athlon 3500+:

  • Flagging a completed recording on an idle system takes 2 min for a 1 hr recording
  • Flagging whilst recording uses about 2% of cpu

Channel Presets

When run on its own the Python program uses decent defaults that work pretty well.

However it's also possible to specify parameters to use for specific channels or programmes. A preset file defines values that override the defaults according to programme title or channel callsign. Only one preset can apply - the first applicable - so care is needed when deciding the order. The title/callsigns are considered to be Python regular expressions so beware of the meta-characters. The 8th field is ignored and so can be used for comments/notes. Specify a preset file using the --presetfile option, like this:

 /usr/local/bin/silence.py %JOBID% %VERBOSEMODE% --loglevel debug --presetfile /home/eric/.mythtv/silence.preset

Once you understand the logging information you can easily tune your own channels/programmes by experimenting with the --preset option directly from a command line until you get decent results. For example;

 silence.py --chanid 1004 --starttime 20130117220000 --loglevel debug --preset "-80,,3,,180"

This is my preset file which customises the processing of 4 regular programmes and 'tunes' some channels.

Script.png silence.preset

 
# presets for silence.py
# use comma separated values: defaults are used for absent values
# For titles/callsign the name is a python regular expressions, case is ignored.
# Re Metachars are # . ^ $ * + ? { } [ ] \ | ( )
# If a title contains one of these, then escape it (using \) or replace it with full stop
# Names are matched to the START of a title/callsign so "e4" also matches "e4+1"
# First name match is used so put specific presets (ie. programmes) before general ones (channels)
#
# title/callsign, threshold, minquiet, mindetect, minbreak, maxsep, padding
# defaults          -75,       0.16,       6,       120,     120,    0.48,
#
frasier,               ,       0.28,        ,          ,      91,        , long pauses in prog
channel 4 news,        ,       1.00,       1,        55,        ,       0, short advert, many silences
milkshake,             ,       0.48,       8,        60,      61,        , ignore short silences in animation/links
rude tube,             ,       0.32,        ,       180,      61,        , ignore short silences in links

channel 4,             ,       0.24,
more 4,                ,       0.24,
dave,               -71,           ,        ,          ,        ,        , loud silences
quest,                 ,           ,        ,          ,      55,        , short silences, long breaks, short ads
channel 5,             ,       0.24,       2,          ,     300,        , cut news out of films 
itv,                   ,           ,        ,          ,        ,     1.0, long pad for films
film 4,                ,           ,        ,          ,        ,     1.0, long pad for films
bbc,                   ,       0.48,       1,        20,     360,       0, pre/post-roll  
cbeebies,              ,       0.48,       1,        20,     360,       0, pre/post-roll  
cbbc,                  ,       0.48,       1,        20,     360,       0, pre/post-roll  

TroubleShooting

  • If you get "Local access to recording not found" errors then ensure your Storage Group directories (mythtv-setup/Storage Groups) have backslashes on the end. See [[1]]
  • If your comflagging jobs report 126/127 adverts found, this signifies an error when trying to run the job. Check the file permissions for the executables.

Code

catagrower.cpp

Script.png catagrower.cpp

 
/* Copyright 2012 Crackers Phipps. */
/* Public domain. */

/* MythTV files are often large. */
#define _FILE_OFFSET_BITS 64

#include <stdio.h>
#include <stdlib.h>
#include <fcntl.h>
#include <unistd.h>

static void usage(const char *name) {
  fprintf(stderr, "Usage: %s <file> <timeout>\n", name);
  fprintf(stderr, "<file>   : file to be monitored.\n");
  fprintf(stderr, "<timeout>: secs to wait for input.\n");
  fprintf(stderr, "The contents of the file will be copied to stdout.\n");
  fprintf(stderr, "Copying will stop when the file has stopped growing.\n");
}

int main(int argc, char **argv) {

  /* Check usage. */
  if (3 != argc) {
    usage(argv[0]);
    exit(1);
  }

  /* Load options. */
  int fd;
  if (-1 == (fd = open(argv[1], O_RDONLY))) {
    fprintf(stderr, "Could not open %s for reading.\n", argv[1]);
    usage(argv[0]);
    exit(2);
  }
  const int timeout = atoi(argv[2]);

#define BUFFSIZE 4096
  int timer = timeout;
  char buffer[BUFFSIZE];
  int bytes;
  while (timer > 0) {
    while (0 != (bytes = read(fd, buffer, BUFFSIZE))) {
      if (-1 == write (STDOUT_FILENO, buffer, bytes)){
          fprintf(stderr, "Write failed.\n");
          exit(3);
        }
      timer = timeout;
    }
    sleep(1);
    timer--;
  }
  return 0;
}

silence.cpp

Script.png silence.cpp

// Based on mausc.c by Tinsel Phipps.
// v1.0 Roger Siddons
// v2.0 Roger Siddons: Flag clusters asap, fix segfaults, optional headers
// v3.0 Roger Siddons: Remove lib dependencies & commfree
// Public domain. Requires libsndfile
// Detects commercial breaks using clusters of audio silences

#include <cstdlib>
#include <cmath>
#include <cerrno>
#include <climits>
#include <deque>
#include <sndfile.h>
#include <unistd.h>

typedef unsigned frameNumber_t;
typedef unsigned frameCount_t;

// Output to python wrapper requires prefix to indicate level
#define DELIMITER "@" // must correlate with python wrapper
char prefixdebug[7] = "debug" DELIMITER;
char prefixinfo[6]  = "info" DELIMITER;
char prefixerr[5]   = "err" DELIMITER;
char prefixcut[5]   = "cut" DELIMITER;

void error(const char* mesg, bool die = true)
{
    printf("%s%s\n", prefixerr, mesg);
    if (die)
        exit(1);
}

namespace Arg
// Program argument management
{
const float kvideoRate = 25.0;  // sample rate in fps (maps time to frame count)
const frameCount_t krateInMins = kvideoRate * 60; // frames per min
int useThreshold;               // Audio level of silence
frameCount_t useMinQuiet;       // Minimum length of a silence to register
unsigned useMinDetect;          // Minimum number of silences that constitute an advert
frameCount_t useMinLength;      // adverts must be at least this long
frameCount_t useMaxSep;         // silences must be closer than this to be in the same cluster
frameCount_t usePad;            // padding for each cut

void usage()
{
    error("Usage: silence <threshold> <minquiet> <mindetect> <minlength> <maxsep> <pad>", false);
    error("<threshold>: (float)  silence threshold in dB.", false);
    error("<minquiet> : (float)  minimum time for silence detection in seconds.", false);
    error("<mindetect>: (float)  minimum number of silences to constitute an advert.", false);
    error("<minlength>: (float)  minimum length of advert break in seconds.", false);
    error("<maxsep>   : (float)  maximum time between silences in an advert break in seconds.", false);
    error("<pad>      : (float)  padding for each cut point in seconds.", false);
    error("AU format audio is expected on stdin.", false);
    error("Example: silence -75 0.1 5 60 90 1 < audio.au");
}

void parse(int argc, char **argv)
// Parse args and convert to useable values (frames)
{
    if (7 != argc)
        usage();

    float argThreshold; // db
    float argMinQuiet; // secs
    float argMinDetect;
    float argMinLength; // secs
    float argMaxSep; // secs
    float argPad; // secs

    /* Load options. */
    if (1 != sscanf(argv[1], "%f", &argThreshold))
        error("Could not parse threshold option into a number");
    if (1 != sscanf(argv[2], "%f", &argMinQuiet))
        error("Could not parse minquiet option into a number");
    if (1 != sscanf(argv[3], "%f", &argMinDetect))
        error("Could not parse mindetect option into a number");
    if (1 != sscanf(argv[4], "%f", &argMinLength))
        error("Could not parse minlength option into a number");
    if (1 != sscanf(argv[5], "%f", &argMaxSep))
        error("Could not parse maxsep option into a number");
    if (1 != sscanf(argv[6], "%f", &argPad))
        error("Could not parse pad option into a number");

    /* Scale threshold to integer range that libsndfile will use. */
    useThreshold = rint(INT_MAX * pow(10, argThreshold / 20));

    /* Scale times to frames. */
    useMinQuiet  = ceil(argMinQuiet * kvideoRate);
    useMinDetect = (int)argMinDetect;
    useMinLength = ceil(argMinLength * kvideoRate);
    useMaxSep    = rint(argMaxSep * kvideoRate + 0.5);
    usePad       = rint(argPad * kvideoRate + 0.5);

    printf("%sThreshold=%.1f, MinQuiet=%.2f, MinDetect=%.1f, MinLength=%.1f, MaxSep=%.1f, Pad=%.2f\n",
           prefixdebug, argThreshold, argMinQuiet, argMinDetect, argMinLength, argMaxSep, argPad);
    printf("%sFrame rate is %.2f, Detecting silences below %d that last for at least %d frames\n",
           prefixdebug, kvideoRate, useThreshold, useMinQuiet);
    printf("%sClusters are composed of a minimum of %d silences closer than %d frames and must be\n",
           prefixdebug, useMinDetect, useMaxSep);
    printf("%slonger than %d frames in total. Cuts will be padded by %d frames\n",
           prefixdebug, useMinLength, usePad);
    printf("%s< preroll, > postroll, - advert, ? too few silences, # too short, = comm flagged\n", prefixdebug);
    printf("%s           Start - End    Start - End      Duration         Interval    Level/Count\n", prefixinfo);
    printf("%s          frame - frame (mmm:ss-mmm:ss) frame (mm:ss.s)  frame (mmm:ss)\n", prefixinfo);
}
}

class Silence
// Defines a silence
{
public:
    enum state_t {progStart, detection, progEnd};
    static const char state_log[3];

    const state_t state;       // type of silence
    const frameNumber_t start; // frame of start
    frameNumber_t end;         // frame of end
    frameCount_t length;       // number of frames
    frameCount_t interval;     // frames between end of last silence & start of this one
    double power;              // average power level

    Silence(frameNumber_t _start, double _power = 0, state_t _state = detection)
        : state(_state), start(_start), end(_start), length(1), interval(0), power(_power) {}

    void extend(frameNumber_t frame, double _power)
    // Define end of the silence
    {
        end = frame;
        length = frame - start + 1;
        // maintain running average power: = (oldpower * (newlength - 1) + newpower)/ newlength
        power += (_power - power)/length;
    }
};
// c++0x doesn't allow initialisation within class
const char Silence::state_log[3] = {'<', ' ', '>'};

class Cluster
// A cluster of silences
{
private:
    void setState()
    {
        if (this->start->start == 1)
            state = preroll;
        else if (this->end->state == Silence::progEnd)
            state = postroll;
        else if (length < Arg::useMinLength)
            state = tooshort;
        else if (silenceCount < Arg::useMinDetect)
            state = toofew;
        else
            state = advert;
    }

public:
    // tooshort..unset are transient states - they may be updated, preroll..postroll are final
    enum state_t {tooshort, toofew, unset, preroll, advert, postroll};
    static const char state_log[6];

    static frameNumber_t completesAt; // frame where the most recent cluster will complete

    state_t state;          // type of cluster
    const Silence* start;   // first silence
    Silence* end;           // last silence
    frameNumber_t padStart, padEnd; // padded cluster start/end frames
    unsigned silenceCount;  // number of silences
    frameCount_t length;    // number of frames
    frameCount_t interval;  // frames between end of last cluster and start of this one

    Cluster(Silence* s) : state(unset), start(s), end(s), silenceCount(1), length(s->length), interval(0)
    {
        completesAt = end->end + Arg::useMaxSep; // finish cluster <maxsep> beyond silence end
        setState();
        // pad everything except pre-rolls
        padStart = (state == preroll ? 1 : start->start + Arg::usePad);
    }

    void extend(Silence* _end)
    // Define end of a cluster
    {
        end = _end;
        silenceCount++;
        length = end->end - start->start + 1;
        completesAt = end->end + Arg::useMaxSep; // finish cluster <maxsep> beyond silence end
        setState();
        // pad everything except post-rolls
        padEnd = end->end - (state == postroll ? 0 : Arg::usePad);
    }
};
// c++0x doesn't allow initialisation within class
const char Cluster::state_log[6] = {'#', '?', '.', '<', '-', '>'};
frameNumber_t Cluster::completesAt = 0;

class ClusterList
// Manages a list of detected silences and a list of assigned clusters
{
protected:
    // list of detected silences
    std::deque<Silence*> silence;

    // list of deduced clusters of the silences
    std::deque<Cluster*> cluster;

public:
    Silence* insertStartSilence()
    // Inserts a fake silence at the front of the silence list
    {
        // create a single frame silence at frame 1 and insert it at front
        Silence* ref = new Silence(1, 0, Silence::progStart);
        silence.push_front(ref);
        return ref;
    }

    void addSilence(Silence* newSilence)
    // Adds a silence detection to the end of the silence list
    {
        // set interval between this & previous silence/prog start
        newSilence->interval = newSilence->start
                - (silence.empty() ? 1 : silence.back()->end - 1);
        // store silence
        silence.push_back(newSilence);
    }

    void addCluster(Cluster* newCluster)
    // Adds a cluster to end of the cluster list
    {
        // set interval between new cluster & previous one/prog start
        newCluster->interval = newCluster->start->start
                - (cluster.empty() ? 1 : cluster.back()->end->end - 1);
        // store cluster
        cluster.push_back(newCluster);
    }
};

Silence* currentSilence; // the silence currently being detected/built
Cluster* currentCluster; // the cluster currently being built
ClusterList* clist;      // List of completed silences & clusters

void report(const char* err,
            const char type,
            const char* msg1,
            const frameNumber_t start,
            const frameNumber_t end,
            const frameNumber_t interval,
            const int power)
// Logs silences/clusters/cuts in a standard format
{
    frameCount_t duration = end - start + 1;

    printf("%s%c %7s %6d-%6d (%3d:%02ld-%3d:%02ld), %4d (%2d:%04.1f), %5d (%3d:%02ld), [%7d]\n",
           err, type, msg1, start, end,
           (start+13) / Arg::krateInMins, lrint(start / Arg::kvideoRate) % 60,
           (end+13) / Arg::krateInMins, lrint(end / Arg::kvideoRate) % 60,
           duration, (duration+1) / Arg::krateInMins, fmod(duration / Arg::kvideoRate, 60),
           interval, (interval+13) / Arg::krateInMins, lrint(interval / Arg::kvideoRate) % 60, power);
}

void processSilence()
// Process a silence detection
{
    // ignore detections that are too short
    if (currentSilence->state == Silence::detection && currentSilence->length < Arg::useMinQuiet)
    {
        // throw it away
        delete currentSilence;
        currentSilence = NULL;
    }
    else
    {
        // record new silence
        clist->addSilence(currentSilence);

        // assign it to a cluster
        if (currentCluster)
        {
            // add to existing cluster
            currentCluster->extend(currentSilence);
        }
        else if (currentSilence->interval <= Arg::useMaxSep) // only possible for very first silence
        {
            // First silence is close to prog start so extend cluster to the start
            // by inserting a fake silence at prog start and starting the cluster there
            currentCluster = new Cluster(clist->insertStartSilence());
            currentCluster->extend(currentSilence);
        }
        else
        {
            // this silence is the start of a new cluster
            currentCluster = new Cluster(currentSilence);
        }
        report(prefixdebug, currentSilence->state_log[currentSilence->state], "Silence",
               currentSilence->start, currentSilence->end,
               currentSilence->interval, currentSilence->power);

        // silence is now owned by the list, start looking for next
        currentSilence = NULL;
    }
}

void processCluster()
// Process a completed cluster
{
    // record new cluster
    clist->addCluster(currentCluster);

    report(prefixinfo, currentCluster->state_log[currentCluster->state], "Cluster",
           currentCluster->start->start, currentCluster->end->end,
           currentCluster->interval, currentCluster->silenceCount);

    // only flag clusters at final state
    if (currentCluster->state > Cluster::unset)
        report(prefixcut, '=', "Cut", currentCluster->padStart, currentCluster->padEnd, 0, 0);

    // cluster is now owned by the list, start looking for next
    currentCluster = NULL;
}

int main(int argc, char **argv)
// Detect silences and allocate to clusters
{
    // Remove logging prefixes if writing to terminal
    if (isatty(1))
        prefixcut[0] = prefixinfo[0] = prefixdebug[0] = prefixerr[0] = '\0';

    // flush output buffer after every line
    setvbuf(stdout, NULL, _IOLBF, 0);

    Arg::parse(argc, argv);

    /* Check the input is an audiofile. */
    SF_INFO metadata;
    SNDFILE* input = sf_open_fd(STDIN_FILENO, SFM_READ, &metadata, SF_FALSE);
    if (NULL == input) {
        error("libsndfile error:", false);
        error(sf_strerror(NULL));
    }

    /* Allocate data buffer to contain audio data from one video frame. */
    const size_t frameSamples = metadata.channels * metadata.samplerate / Arg::kvideoRate;

    int* samples = (int*)malloc(frameSamples * sizeof(int));
    if (NULL == samples)
        error("Couldn't allocate memory");

    // create silence/cluster list
    clist = new ClusterList();

    // Process the input one frame at a time and process cuts along the way.
    frameNumber_t frames = 0;
    while (frameSamples == static_cast<size_t>(sf_read_int(input, samples, frameSamples)))
    {
        frames++;

        // determine average audio level in this frame
        long avgabs = 0;
        for (unsigned i = 0; i < frameSamples; i++)
            avgabs += abs(samples[i]);
        avgabs = avgabs / frameSamples;

        // check for a silence
        if (avgabs < Arg::useThreshold)
        {
            if (currentSilence)
            {
                // extend current silence
                currentSilence->extend(frames, avgabs);
            }
            else // transition to silence
            {
                // start a new silence
                currentSilence = new Silence(frames, avgabs);
            }
        }
        else if (currentSilence) // transition out of silence
        {
            processSilence();
        }
        // in noise: check for cluster completion
        else if (currentCluster && frames > currentCluster->completesAt)
        {
            processCluster();
        }
    }
    // Complete any current silence (prog may have finished in silence)
    if (currentSilence)
    {
        processSilence();
    }
    // extend any cluster close to prog end
    if (currentCluster && frames <= currentCluster->completesAt)
    {
        // generate a silence at prog end and extend cluster to it
        currentSilence = new Silence(frames, 0, Silence::progEnd);
        processSilence();
    }
    // Complete any final cluster
    if (currentCluster)
    {
        processCluster();
    }
}

silence.py

Script.png silence.py

#!/usr/bin/env python
# Build a skiplist from silence in the audio track.
# Roger Siddons v1.0
# v2.0 Fix progid for job/player messages
# v3.0 Send player messages via Python
# v3.1 Fix commflag status, pad preset. Improve style & make Python 3 compatible

import MythTV
import os
import subprocess
import argparse
import collections
import re
import sys

kExe_Catagrower = '/usr/local/bin/catagrower'
kExe_Silence = '/usr/local/bin/silence'
kUpmix_Channels = '1'
kInput_Timeout = '60'


class MYLOG(MythTV.MythLog):
    "A specialised logger"

    def __init__(self, db):
        "Initialise logging"
        MythTV.MythLog.__init__(self, 'm', db)

    def log(self, msg, level=MythTV.MythLog.INFO):
        "Log message"
        # prepend string to msg so that rsyslog routes it to correct logfile
        MythTV.MythLog.log(self, MythTV.MythLog.COMMFLAG, level,
            'mythcommflag: ' + msg.rstrip('\n'))


class PRESET:
    "Manages the presets (parameters passed to the detection algorithm)"

    # define arg ordering and default values
    argname = ['thresh', 'minquiet', 'mindetect', 'minbreak', 'maxsep', 'pad']
    argval  = [  -75,       0.16,        6,          120,       120,    0.48]
    # dictionary holds value for each arg
    argdict = collections.OrderedDict(list(zip(argname, argval)))

    def _validate(self, k, v):
        "Converts arg input from string to float or None if invalid/not supplied"
        if v is None or v == '':
            return k, None
        try:
            return k, float(v)
        except ValueError:
            self.logger.log('Preset ' + k + ' (' + str(v) + ') is invalid - will use default',
                MYLOG.ERR)
            return k, None

    def __init__(self, _logger):
        "Initialise preset manager"
        self.logger = _logger

    def getFromArg(self, line):
        "Parses preset values from command-line string"
        self.logger.log('Parsing presets from "' + line + '"', MYLOG.DEBUG)
        if line:  # ignore empty string
            vals = [i.strip() for i in line.split(',')]  # split individual params
            # convert supplied values to float & match to appropriate arg name
            validargs = list(map(self._validate, self.argname, vals[0:len(self.argname)]))
            # remove missing/invalid values from list & replace default values with the rest
            self.argdict.update(v for v in validargs if v[1] is not None)

    def getFromFile(self, filename, title, callsign):
        "Gets preset values from a file"
        self.logger.log('Using preset file "' + filename + '"', MYLOG.DEBUG)
        try:
            with open(filename) as presets:
                for rawline in presets:
                    line = rawline.strip()
                    if line and (not line.startswith('#')):  # ignore empty & comment lines
                        vals = [i.strip() for i in line.split(',')]  # split individual params
                        # match preset name to recording title or channel
                        pattern = re.compile(vals[0], re.IGNORECASE)
                        if pattern.match(title) or pattern.match(callsign):
                            self.logger.log('Using preset "' + line.strip() + '"')
                            # convert supplied values to float & match to appropriate arg name
                            validargs = list(map(self._validate, self.argname,
                                                 vals[1:1 + len(self.argname)]))
                            # remove missing/invalid values from list &
                            # replace default values with the rest
                            self.argdict.update(v for v in validargs if v[1] is not None)
                            break
                else:
                    self.logger.log('No preset found for "' + title + '" or "' + callsign + '"')
        except IOError:
            self.logger.log('Presets file "' + filename + '" not found', MYLOG.ERR)
        return self.argdict

    def getValues(self):
        "Returns params as a list of strings"
        return [str(i) for i in list(self.argdict.values())]


def main():
    "Commflag a recording"

    # define options
    parser = argparse.ArgumentParser(description='Commflagger')
    parser.add_argument('--preset',
        help='Specify values as "Threshold, MinQuiet, MinDetect, MinLength, MaxSep, Pad"')
    parser.add_argument('--presetfile', help='Specify file containing preset values')
    parser.add_argument('--chanid', help='Use chanid for manual operation')
    parser.add_argument('--starttime', help='Use starttime for manual operation')
    parser.add_argument('jobid', nargs='?', help='Myth job id')

    # must set up log attributes before Db locks them
    MYLOG.loadArgParse(parser)
    MYLOG._setmask(MYLOG.COMMFLAG)

    # parse options
    args = parser.parse_args()

    db = MythTV.MythDB()
    logger = MYLOG(db)
    be = MythTV.BECache(None, False, db)

    if args.jobid:
        job = MythTV.Job(args.jobid, db)
        chanid = job.chanid
        starttime = job.starttime
        timeout = kInput_Timeout
    elif args.chanid and args.starttime:
        job = None
        chanid = args.chanid
        starttime = args.starttime
        timeout = '1'
    else:
        logger.log('Both chanid and starttime must be specified', MYLOG.ERR)
        sys.exit(1)

    # get recording
    try:
        rec = MythTV.Recorded((chanid, starttime), db)
    except:
        if job:
            job.update({'status': job.ERRORED, 'comment': 'ERROR: Could not find recording.'})
        logger.log('Could not find recording', MYLOG.ERR)
        sys.exit(1)

    channel = MythTV.Channel(chanid, db)

    logger.log('')
    logger.log('Processing: ' + str(channel.callsign) + ', ' + str(rec.starttime)
        + ', "' + str(rec.title) + ' - ' + str(rec.subtitle) + '"')

    sg = MythTV.findfile(rec.basename, rec.storagegroup, db)
    if sg is None:
        if job:
            job.update({'status': job.ERRORED,
                'comment': 'ERROR: Local access to recording not found.'})
        logger.log('Local access to recording not found', MYLOG.ERR)
        sys.exit(1)

    # player update message needs prog id (with time in Qt::ISODate format)
    progId = str(chanid) + '_' + str(starttime).replace(' ', 'T')

    # create params with default values
    param = PRESET(logger)
    # read any supplied presets
    if args.preset:
        param.getFromArg(args.preset)
    elif args.presetfile:  # use preset file
        param.getFromFile(args.presetfile, rec.title, channel.callsign)

    infile = os.path.join(sg.dirname, rec.basename)

    # Purge any existing skip list and flag as in-progress
    rec.commflagged = 2
    rec.markup.clean()
    rec.update()

    # Write out the file contents and keep going till recording is finished.
    p1 = subprocess.Popen([kExe_Catagrower, infile, timeout], stdout=subprocess.PIPE)
    # Pipe through ffmpeg to extract uncompressed audio stream.
    p2 = subprocess.Popen(["mythffmpeg", "-loglevel", "quiet", "-i", "pipe:0",
                          "-ar", "8000", "-f", "au", "-ac", kUpmix_Channels, "-"],
                          stdin=p1.stdout, stdout=subprocess.PIPE)
    # Pipe to silence which will spit out formatted log lines
    p3 = subprocess.Popen([kExe_Silence] + param.getValues(), stdin=p2.stdout,
                          stdout=subprocess.PIPE)

    # Process log output
    breaks = 0
    level = {'info': MYLOG.INFO, 'debug': MYLOG.DEBUG, 'err': MYLOG.ERR}
    while True:
        line = p3.stdout.readline()
        if line:
            flag, info = line.split('@', 1)
            if flag == 'cut':
                # extract numbers from log
                numbers = re.findall('\d+', info)
                logger.log(info)
                # mark advert in database
                rec.markup.append(int(numbers[0]), rec.markup.MARK_COMM_START, None)
                rec.markup.append(int(numbers[1]), rec.markup.MARK_COMM_END, None)
                rec.update()
                breaks += 1
                # send advert skiplist to MythPlayers
                tuplelist = [(str(x) + ':' + str(rec.markup.MARK_COMM_START),
                             str(y) + ':' + str(rec.markup.MARK_COMM_END))
                             for x, y in rec.markup.getskiplist()]
                mesg = 'COMMFLAG_UPDATE ' + progId + ' ' \
                    + ','.join([x for tuple in tuplelist for x in tuple])
                #logger.log('  Sending ' + mesg,  MYLOG.DEBUG)
                result = be.backendCommand("MESSAGE[]:[]" + mesg)
                if result != 'OK':
                    logger.log('Backend message failed, response = %s, message = MESSAGE[]:[]%s'
                               % (result, mesg), MYLOG.ERR)
            elif flag in level:
                logger.log(info, level.get(flag))
            else:  # unexpected prefix
                # use warning for unexpected log levels
                logger.log(flag, MYLOG.WARNING)
        else:
            break

    logger.log('Detected %s adverts.' % breaks)
    if job:
        job.update({'status': 272, 'comment': 'Detected %s adverts.' % breaks})

    # Signal comflagging has finished
    rec.commflagged = 1
    rec.update()

if __name__ == '__main__':
    main()

Makefile

Script.png Makefile

CC        = g++
CFLAGS    = -c -Wall -std=c++0x
LIBPATH   = -L/usr/lib
TARGETDIR = /usr/local/bin

.PHONY: clean install

all: silence catagrower
	
catagrower: catagrower.o
	$(CC) catagrower.o -o $@
	
silence: silence.o
	$(CC) silence.o -o $@ $(LIBPATH) -lsndfile

.cpp.o:
	$(CC) $(CFLAGS) $< -o $@

install: silence catagrower silence.py
	install -p -t $(TARGETDIR) $^

clean: 
	-rm -f silence catagrower *.o