SPTK Version 4.3

What's Changed

• Add plp by @takenori-y in #55
• Add alaw by @takenori-y in #56
• Fix build against gcc-13 (missing <cstdint> includes) by @trofi in #57
• Add onehot by @takenori-y in #61
• Add iltcdf by @takenori-y in #63
• Add pnorm and ipnorm by @takenori-y in #65
• Support sawtooth generation in pitch_mark and pitch2sin by @takenori-y in #67 #73
• Add mode by @takenori-y in #68
• Support cumulative mode in vsum by @takenori-y in #71
• Add vprod by @takenori-y in #72

New Contributor

• @trofi made their first contribution in #57

Acknowledgments

• Keiichi Tokuda @k1tokuda
• Keiichiro Oura @uratec
• Takenori Yoshimura @takenori-y
• Takato Fujimoto @taka19

SPTK Version 4.2

New features

• Enable to whiten residual signal (amgcep -k) by @takenori-y in #27
• Enable to change of signal in unvoiced region (excite -n) by @takenori-y in #28
• Add ap command by @takenori-y in #30
• Add pitch_spec command by @takenori-y in #34
• Add world_synth command by @takenori-y in #35
• Support Harvest (pitch -a 4) by @takenori-y in #36
• Support recursive vector merge (merge -q) by @takenori-y in #44
• Add pitch2sin by @takenori-y in #46 and #48
• Convert GCI to sinusoidal waveform (pitch_mark -o 3) by @takenori-y in #49
• Support statistics merge (vstat -o 7) by @takenori-y in #51
• Windows support by @takenori-y in #42

Minor fixes

• Add cmake find_package compatibility by @ascii255 in #33
• Remove +e option from draw command by @takenori-y in #41
• Fix bug in magic_intpl by @takenori-y in #43
• Reduce computational cost of vstat by @takenori-y in #50
• Fix minmax by @takenori-y in #53

Acknowledgments

• Keiichi Tokuda @k1tokuda
• Keiichiro Oura @uratec
• Takenori Yoshimura @takenori-y
• Takato Fujimoto @taka19

SPTK Version 4.1

Merry Christmas to you 🎉

New Features

• Calculating autocorrelation from spectrum (acorr -q)
• Conversion impulse response to cepstrum (mpir2c)
• Drawing spectrogram (gspecgram)
• Dynamic range compression (drc)
• Magic number interpolation (magic_intpl)
• Median filter (medfilt)

Minor fixes

• Option in drawing commands
• Thread safety of pitch
• Small bugs

Acknowledgments

• Keiichi Tokuda @k1tokuda
• Keiichiro Oura @uratec
• Takenori Yoshimura @takenori-y
• Takato Fujimoto @taka19

SPTK Version 4.0

Major Changes from SPTK3

• Signal processing tools were written in C++ instead of C
• Input and output types were changed to double from float
• Drawing commands were implemented in Python
• Following commands were obsoleted
  • acep, agcep, and amcep
  • bell
  • c2sp
  • cat2 and echo2
  • da
  • ds, us, us16, and uscd
  • fig
  • gc2gc
  • gcep, mcep, and uels
  • glsadf, lmadf, and mlsadf
  • ivq and vq
  • lsp2sp
  • mgc2mgclsp
  • psgr and xgr
  • raw2wav, wav2raw, wavjoin, and wavsplit
• Following commands were separated
  • dtw (dtw and dtw_merge)
  • mglsadf (mglsadf and imglsadf)
  • train (train and mseq)
  • ulaw (ulaw and iulaw)
  • vstat (vstat and median)
• Following commands were renamed
  • c2ir to c2mpir
  • mgclsp2sp to mglsp2sp

New Features

• Conversion from/to log area ratio (lar2par and par2lar)
• Entropy calculation (entropy)
• Huffman coding (huffman, huffman_encode, and huffman_decode)
• Mel-cepstrum postfilter (mcpf)
• Mel-filter-bank extraction (fbank)
• Nonrecursive MLPG (mlpg -R 1)
• Pitch extraction by DIO used in WORLD (pitch -a 3)
• Scalar quantization (quantize and dequantize)
• Stability check of LPC coefficients (lpccheck)
• Subband decomposition (pqmf and ipqmf)
• Windows build support (only static library)

Acknowledgments

• Keiichi Tokuda @k1tokuda
• Keiichiro Oura @uratec
• Takenori Yoshimura @takenori-y
• Takato Fujimoto @taka19