rVAD2.0

所属分类:语音合成
开发工具:matlab
文件大小:8240KB
下载次数:2
上传日期:2019-06-22 20:35:00
上 传 者reagan65
说明:  unsupervised segment-based method for robust voice activity detection (rVAD)

文件列表:
rVAD2.0\.DS_Store (6148, 2017-11-28)
rVAD2.0\aurora2read.m (329, 2017-11-29)
rVAD2.0\enframe.m (4298, 2017-11-25)
rVAD2.0\estnoiseg.m (7306, 2014-01-16)
rVAD2.0\estnoisem.m (16236, 2014-01-16)
rVAD2.0\estnoisem_noiseseg.m (18179, 2017-11-25)
rVAD2.0\filtbankm.m (14732, 2017-11-25)
rVAD2.0\findpeaks.m (4237, 2017-11-25)
rVAD2.0\fxpefac.m (16316, 2017-11-25)
rVAD2.0\gaussmixp.m (8257, 2017-11-25)
rVAD2.0\irfft.m (3324, 2017-11-25)
rVAD2.0\pitchblockdetect.m (1076, 2017-11-25)
rVAD2.0\pitchestm.m (796, 2017-11-25)
rVAD2.0\rfft.m (1868, 2017-11-25)
rVAD2.0\sflux.m (942, 2017-11-29)
rVAD2.0\snre_highenergy.m (2748, 2017-12-01)
rVAD2.0\snre_vad.m (5695, 2019-03-16)
rVAD2.0\specsub.m (14837, 2014-01-16)
rVAD2.0\specsub_noiseseg_lfn.m (15802, 2017-11-25)
rVAD2.0\speech01.wav (49490, 2019-05-30)
rVAD2.0\speech16.wav (98936, 2019-06-22)
rVAD2.0\spgrambw.m (26641, 2017-11-25)
rVAD2.0\stdspectrum.m (20410, 2017-11-25)
rVAD2.0\test1.pk (90496, 2019-06-22)
rVAD2.0\test1.wav (7715152, 2019-06-22)
rVAD2.0\test_016.wav (1285896, 2019-06-22)
rVAD2.0\vad.m (3246, 2019-03-16)
rVAD2.0\vadbatch_1folder_diffpathes.m (1404, 2017-11-25)
rVAD2.0\voicebox.m (8766, 2017-11-25)
rVAD2.0\winenvar.m (1734, 2017-11-25)
__MACOSX\._rVAD2.0 (190, 2019-03-16)
__MACOSX\rVAD2.0\._.DS_Store (120, 2017-11-28)
__MACOSX\rVAD2.0\._aurora2read.m (434, 2017-11-29)
__MACOSX\rVAD2.0\._enframe.m (190, 2017-11-25)
__MACOSX\rVAD2.0\._estnoiseg.m (212, 2014-01-16)
__MACOSX\rVAD2.0\._estnoisem.m (212, 2014-01-16)
__MACOSX\rVAD2.0\._estnoisem_noiseseg.m (190, 2017-11-25)
__MACOSX\rVAD2.0\._filtbankm.m (190, 2017-11-25)
__MACOSX\rVAD2.0\._findpeaks.m (190, 2017-11-25)
... ...

Noise robust voice activity detection algorithm (rVAD). Version 2.0 28 Nov 2017 Usage: vad(finwav, fvad) vad(finwav, fvad, opts) vad(finwav, fvad, opts, vadThres). where finwav is the input WAVE file path and name, fvad is the output VAD file path and name, opts can be 0 for using pitch (default option) or 1 for using flatness (significantly faster at the cost of slightly reduced accuracy), and finally vadThres is the threshold for VAD. Refer to vad.m for more detailed explanation. The code has been tested on Matlab R2016a. Refs: [1] Z.-H. Tan, A.k. Sarkara and N. Dehak, "rVAD: an unsupervised segment-based robust voice activity detection method," Manuscript submitted for publication. [2] Z.-H. Tan and B. Lindberg, "Low-complexity variable frame rate analysis for speech recognition and voice activity detection, IEEE Journal of Selected Topics in Signal Processing, vol. 4, no. 5, pp. 7***-807, 2010. Contact: Prof Zheng-Hua Tan Aalborg University, Denmark zt@es.aau.dk http://kom.aau.dk/~zt/

近期下载者

相关文件


收藏者