ch_track(1) [debian man page]
CH_TRACK(1) BSD General Commands Manual CH_TRACK(1) NAME
ch_track -- change/copy track file SYNOPSIS
ch_track [-h] [-itype file type] [-ctype contour type] [-s frame spacing] [-c channels] [-start time] [-end time] [-from frame] [-to frame] [-o file] [-otype file type] [-S frame spacing] [-info] [-track_names file] [-diff] [-delta length] [-sm time] [-smtype median | mean] [-style style] [-t threshold] [-neg label] [-pos label] [-pc longest | first] input file DESCRIPTION
ch_track copies an input track file to an output track file, optionally performing various operations along the way. The following option flags are recognized: -h Print a short summary of options to standard output. -itype file type Input file type (optional). If no type is specified, type is automatically derived from the input file's header. The list of sup- ported types may depend on your particular Speech Tools installation. For a full listing, see the output of the -h option. -ctype F0 | track Contour type, either F0 (fundamental frequency) or track. -s time Frame spacing of input in seconds, for unheadered input file. -c channels Select a subset of channels (starting from 0). Tracks can have multiple channels. This option specifies a list of channel num- bers which are to be used for processing. -start time Extract track starting at this time, specified in seconds. -end time Extract track ending at this time, specified in seconds. -from frame Extract track starting at this offset, specified in frames. -to frame Extract track ending at this offset, specified in frames. -o file Filename to write output to. Defaults to standard output. -otype file type Output file type. If unspecified, ascii is assumed. For the full list of supported types, see the output of the -h option. -S time Frame spacing of output in seconds. If this is different from the input spacing, the contour will be resampled. -info Print information about the input file and its headers. This option gives useful information such as file length, file type, and channel names. No other actions are taken, and no output file produced. -track_names file File containing new names for output channels -diff Differentiate contour. This performs simple numerical differentiation on the contour by subtracting the amplitude of the current frame from the amplitude of the next. Although quick, this technique is crude and not recommended as the estimation of the derivate is done on only one point. -delta length Make delta coefficients (better form of differentiation). The argument to this option is the regression length of the delta cal- culation and can be between 2 and 4. -sm time Length of smoothing window in seconds. Various types of smoothing are available for tracks. This option specifies length of the smoothing window which affects the degree of smoothing, i.e. a longer value means more smoothing. -smtype median | mean Type of smoothing. -style style Convert track to another form. Currently only one form, "label", is supported. This uses a specified cutoff to make a label file, with two labels, one for above the cutoff (see the -pos option), and one for below (see the -neg option). -t threshold Threshold for track to label conversion. -neg label Name of negative label in track to label conversion. -pos label Name of positive label in track to label conversion. -pc longest | first Combind given tracks in parallel. If option is "longest", pad shorter tracks to longest, else if "first", pad or cut them as appropriate to match the length of the first input track. SEE ALSO
ch_lab(1) ch_utt(1) Edinburgh Speech Tools April 5, 2001 Edinburgh Speech Tools
Check Out this Related Man Page
CH_WAVE(1) BSD General Commands Manual CH_WAVE(1) NAME
ch_wave -- change/copy/combine waveform files SYNOPSIS
ch_wave [-h] [-itype file type] [-n channels] [-f sample rate] [-ibo byte order] [-iswap] [-istype sample type] [-c channel] [-start seconds] [-end seconds] [-from sample] [-to sample] [-o output file] [-otype file type] [-F sample rate] [-obo byte order] [-oswap] [-ostype sample type] [-scale factor] [-scaleN factor] [-lpfilter frequency] [-hpfilter freqency] [-forder order] [-fafter] [-info] [-add] [-pc LONGEST | FIRST] [-key keylab file] [-divide] [-ext file extension] [-extract file] input files ... DESCRIPTION
ch_wave performs various operations on an input waveform file and writes it out to another file. Among other things, it can extract subsec- tions or individual channels, resample, rescale, mix down channels, and perform simple filtering operations. The following option flags are recognized: -h Options help -itype file type Input file type (optional). If set to raw, this indicates that the input file does not have a header. While this can be used to specify file types other than raw, this is rarely used for other purposes as the file type of all the existing supported types can be determined automatically from the file's header. If the input file is unheadered, files are assumed to be shorts (16bit). Supported types are nist, est, esps, snd, riff, aiff, audlab, raw, ascii -n channels Number of channels in an unheadered input file -f sample rate Sample rate in Hertz for an unheadered input file -ibo byte order Input byte order in an unheadered input file: possibliities are: MSB , LSB, native or nonnative. Suns, HP, SGI Mips, M68000 are MSB (big endian) Intel, Alpha, DEC Mips, Vax are LSB (little endian) -iswap Swap bytes. (For use on an unheadered input file) -istype sample type Sample type in an unheadered input file: short, alaw, mulaw, byte, ascii -c channel Select a single channel (starts from 0). Waveforms can have multiple channels. This option extracts a single channel for prog- cessing and discards the rest. -start seconds Extract sub-wave starting at this time, specified in seconds -end seconds Extract sub-wave ending at this time, specified in seconds -from sample Extract sub-wave starting at this sample point -to sample Extract sub-wave ending at this sample point -o output file Output filename. If not specified output is to stdout. -otype file type Output file type, (optional). If no type is Specified the type of the input file is assumed. Supported types are: nist, est, esps, snd, riff, aiff, audlab, raw, ascii -F sample rate Output sample rate in Hz. If this is different from the input sample rate, resampling will occur -obo byte order Output byte order: MSB, LSB, native, or nonnative. Suns, HP, SGI Mips, M68000 are MSB (big endian), Intel, Alpha, DEC Mips, Vax are LSB (little endian) -oswap Swap bytes when saving to output -ostype sample type Output sample type: short, alaw, mulaw, byte or ascii -scale factor Scaling factor. Increase or descrease the amplitude of the whole waveform by the factor given (relative to 1.0) -scaleN factor Scaling factor with normalization. The waveform is scaled to its maximum level, after which it is scaled by the factor given (relative to 1.0) -lpfilter frequency Low pass filter, with cutoff frequency in Hz Filtering is performed by a FIR filter which is built at run time. The order of the filter can be given by -forder. The default value is 199 -hpfilter freqency High pass filter, with cutoff frequency in Hz Filtering is performed by a FIR filter which is built at run time. The order of the filter can be given by -forder. The default value is 199. -forder order Order of FIR filter used for lpfilter and hpfilter. This must be ODD. Sensible values range from 19 (quick but with a shallow rolloff) to 199 (slow but with a steep rolloff). The default is 199. -fafter Do filtering after other operations such as resampling (default : filter before other operations) -info Print information about file and header. This option gives useful information such as file length, sampling rate, number of chan- nels etc No output is produced -add A new single channel waveform is created by adding the corresponding sample points of each input waveform -pc LONGEST | FIRST Combine input waveforms to form a single multichannel waveform. The argument to this option controls how long the new waveform should be. If the option is LONGEST, the output wave if the length of the longest input wave and shorter waves are padded with zeros at the end. If the option is FIRST, the length of the new waveform is the length of the first file on the command line, and subsequent waves are padded or cut to this length -key keylab file Label file designating subsections, for use with -divide. The KEYLAB file is a label file which specifies where chunks (such as individual sentences) in a waveform begin and end. See section on wave extraction. -divide Divide a single input waveform into multiple output waveforms. Each output waveform is extracted from the input waveform by using the KEYLAB file, which specifies the start and stop times for each chunk. The output files are named according to the filename in the KEYLAB file, with extension given by -ext. See section on wave extraction -ext file extension File extension for divided waveforms -extract file Used in conjunction with -key to extract a single section of waveform from the input waveform. The argument is the name of a file given in the file column of the KEYLAB file. EXAMPLES
BUGS
SEE ALSO
ch_track(1) ch_utt(1) na_record(1) na_play(1) Edinburgh Speech Tools April 5, 2001 Edinburgh Speech Tools