I-Vectors for speech activity detection

I-Vectors are low dimensional front-end features known to effectively preserve the total variability of the signal. Motivated by their successful use for several classification problems such as speaker, language and face recognition, this paper introduces i-vectors for the task of speech activity detection (SAD). In contrast to most state-of-the-art SAD methods that operate at the frame or segment level, this paper proposes a cluster-based SAD, for which two algorithms were investigated: the first is based on generalized likelihood ratio (GLR) and Bayesian information criterion (BIC) for segmentation and clustering, whereas the second uses K-means and GMM clustering. Furthermore, we explore the use of i-vectors based on different low-level features including MFCC, PLP and RASTA-PLP, as well as fusion of such systems at the decision level. We show the feasibility and the effectiveness of the proposed system in comparison with a frame-based GMM baseline using the challenging RATS dataset in the context of the 2015 NIST OpenSAD evaluation.

[1]  Malcolm Slaney,et al.  Construction and evaluation of a robust multifeature speech/music discriminator , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Brian Kingsbury,et al.  Improvements to the IBM speech activity detection system for the DARPA RATS program , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  Florin Curelaru,et al.  Front-End Factor Analysis For Speaker Verification , 2018, 2018 International Conference on Communications (COMM).

[4]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[5]  Jianwu Dang,et al.  Voice Activity Detection Based on an Unsupervised Learning Framework , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[6]  Yun Lei,et al.  Softsad: Integrated frame-based speech confidence for speaker recognition , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[7]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[8]  Ponani S. Gopalakrishnan,et al.  Clustering via the Bayesian information criterion with applications in speech recognition , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[9]  Pascal Druyts,et al.  Applying Logistic Regression to the Fusion of the NIST'99 1-Speaker Submissions , 2000, Digit. Signal Process..

[10]  Herbert Gish,et al.  Segregation of speakers for speech recognition and speaker identification , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[11]  Jean-Luc Gauvain,et al.  Improving Speaker Diarization , 2004 .

[12]  Elie el Khoury,et al.  Improved speaker diarization system for meetings , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[13]  Thomas Hain,et al.  Segmentation and classification of broadcast news audio , 1998, ICSLP.

[14]  Tomi Kinnunen,et al.  A practical, self-adaptive voice activity detector for speaker verification with noisy telephone and microphone data , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[15]  E. Shlomot,et al.  ITU-T Recommendation G.729 Annex B: a silence compression scheme for use with G.729 optimized for V.70 digital simultaneous voice and data applications , 1997, IEEE Commun. Mag..

[16]  J. Rissanen.  Stochastic Complexity in Statistical Inquiry Theory , 1989 .

[17]  Douglas A. Reynolds,et al.  Speaker Verification Using Adapted Gaussian Mixture Models , 2000, Digit. Signal Process..

[18]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[19]  Nicholas W. D. Evans,et al.  Speaker Diarization: A Review of Recent Research , 2010, IEEE Transactions on Audio, Speech, and Language Processing.

[20]  Themos Stafylakis,et al.  Supervised/Unsupervised Voice Activity Detectors for Text-dependent Speaker Recognition on the RSR2015 Corpus , 2014, Odyssey.

[21]  Kevin Walker,et al.  The RATS Collection: Supporting HLT Research with Degraded Audio Data , 2014, LREC.

[22]  Björn W. Schuller,et al.  Real-life voice activity detection with LSTM Recurrent Neural Networks and an application to Hollywood movies , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[23]  James H. Elder,et al.  Probabilistic Linear Discriminant Analysis for Inferences About Identity , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[24]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[25]  Mark Liberman,et al.  Speech activity detection on youtube using deep neural networks , 2013, INTERSPEECH.

[26]  Daniel Garcia-Romero,et al.  Analysis of i-vector Length Normalization in Speaker Recognition Systems , 2011, INTERSPEECH.

[27]  Zheng-Hua Tan,et al.  Low-Complexity Variable Frame Rate Analysis for Speech Recognition and Voice Activity Detection , 2010, IEEE Journal of Selected Topics in Signal Processing.

[28]  Thad Hughes,et al.  Recurrent neural networks for voice activity detection , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[29]  Yun Lei,et al.  A noise-robust system for NIST 2012 speaker recognition evaluation , 2013, INTERSPEECH.