An Application of Recurrent Neural Networks to Discriminative Keyword Spotting

The goal of keyword spotting is to detect the presence of specific spoken words in unconstrained speech. The majority of keyword spotting systems are based on generative hidden Markov models and lack discriminative capabilities. However, discriminative keyword spotting systems are currently based on frame-level posterior probabilities of sub-word units. This paper presents a discriminative keyword spotting system based on recurrent neural networks only, that uses information from long time spans to estimate word-level posterior probabilities. In a keyword spotting task on a large database of unconstrained speech the system achieved a keyword spotting accuracy of 84.5%

[1]  Chin-Hui Lee,et al.  Automatic recognition of keywords in unconstrained speech using hidden Markov models , 1990, IEEE Trans. Acoust. Speech Signal Process..

[2]  Hervé Bourlard,et al.  Connectionist Speech Recognition: A Hybrid Approach , 1993 .

[3]  Anthony J. Robinson,et al.  An application of recurrent nets to phone probability estimation , 1994, IEEE Trans. Neural Networks.

[4]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[5]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[6]  Hervé Bourlard,et al.  Iterative Posterior-Based Keyword Spotting Without Filler Models , 1999 .

[7]  Pedro García-Teodoro,et al.  Different confidence measures for word verification in speech recognition , 2000, Speech Commun..

[8]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[9]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[10]  Jürgen Schmidhuber,et al.  Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition , 2005, ICANN.

[11]  Rachna Vargiya,et al.  A new evaluation criteria for keyword spotting techniques and a new algorithm , 2005, INTERSPEECH.

[12]  Danilo P. Mandic,et al.  Artificial Neural Networks: Formal Models and Their Applications - ICANN 2005 , 2005 .

[13]  Marius-Calin Silaghi.  Spotting Subsequences Matching an HMM Using the Average Observation Probability Criteria with Application to Keyword Spotting , 2005, AAAI.

[14]  Samy Bengio,et al.  Posterior based keyword spotting with a priori thresholds , 2006, INTERSPEECH.

[15]  Jürgen Schmidhuber,et al.  Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks , 2006, ICML.

[16]  Jürgen Schmidhuber,et al.  Sequence Labelling in Structured Domains with Hierarchical Recurrent Neural Networks , 2007, IJCAI.

[17]  Samy Bengio,et al.  Discriminative keyword spotting , 2009, Speech Commun..