Subspace Gaussian Mixture Models for vectorial HMM-states representation

In this paper we present a vectorial representation of the HMM states that is inspired by the Subspace Gaussian Mixture Models paradigm (SGMM). This vectorial representation of states will make possible a large number of applications, such as HMM-states clustering and graphical visualization. Thanks to this representation, the Hidden Markov Model (HMM) states can be seen as sets of points in multi-dimensional space and then can be studied using statistical data analysis techniques. In this paper, we show how this representation can be obtained and used for tying states of an HHM-based automatic speech recognition system without any use of linguistic or phonetic knowledge. In experiments, this approach achieves significant and stable gain, while conserving the classical approach based on decision trees. We also show how it can be used for graphical visualization, which can be useful in other domains like phonetics or clinical phonetics.

[1]  Kai Feng,et al.  SUBSPACE GAUSSIAN MIXTURE MODELS FOR SPEECH RECOGNITION , 2009 .

[2]  Georges Linarès,et al.  A simplified Subspace Gaussian Mixture to compact acoustic models for speech recognition , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  Guillaume Gravier,et al.  The ester 2 evaluation campaign for the rich transcription of French radio broadcasts , 2009, INTERSPEECH.

[4]  Wu Chou,et al.  Decision tree state tying based on segmental clustering for acoustic modeling , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[5]  Steve J. Young,et al.  The use of state tying in continuous speech recognition , 1993, EUROSPEECH.

[6]  Etienne Barnard,et al.  Phone clustering using the Bhattacharyya distance , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[7]  Hermann Ney,et al.  Automatic question generation for decision tree based state tying , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[8]  L. R. Rabiner,et al.  A probabilistic distance measure for hidden Markov models , 1985, AT&T Technical Journal.

[9]  Joachim Köhler,et al.  Multi-lingual phoneme recognition exploiting acoustic-phonetic similarities of sounds , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[10]  Driss Matrouf,et al.  A straightforward and efficient implementation of the factor analysis model for speaker verification , 2007, INTERSPEECH.

[11]  Patrick Kenny,et al.  Support vector machines versus fast scoring in the low-dimensional total variability space for speaker verification , 2009, INTERSPEECH.

[12]  Peter Beyerlein,et al.  A bottom-up approach for handling unseen triphones in large vocabulary continuous speech recognition , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[13]  J. Kohler.  Multi-lingual phoneme recognition exploiting acoustic-phonetic similarities of sounds , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[14]  Patrick Kenny,et al.  Optimal tying of HMM mixture densities using decision trees , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.