Rich system combination for keyword spotting in noisy and acoustically heterogeneous audio streams

We address the problem of retrieving spoken information from noisy and heterogeneous audio archives using system combination with a rich and diverse set of noise-robust modules. Audio search applications so far have focused on constrained domains or genres and not-so-noisy and heterogeneous acoustic or channel conditions. In this paper, our focus is to improve the accuracy of a keyword spotting system in highly degraded and diverse channel conditions by employing multiple recognition systems in parallel with different robust frontends and modeling choices, as well as different representations during audio indexing and search (words vs. subword units). After aligning keyword hits from different systems, we employ system combination at the score level using a logistic-regression-based classifier. Side information such as the output of an acoustic condition identification module is used to guide system combination system that is trained on a held-out dataset. Lattice-based indexing and search is used in all keyword spotting systems. We present improvements in probability-miss at a fixed probability-false-alarm by employing our proposed rich system combination approach on DARPA Robust Automatic Transcription of Speech (RATS) Phase-I evaluation data that contains highly degraded channel recordings (signal-to-noise ratio levels as low as 0 dB) and different channel characteristics.

[1]  Ellen M. Voorhees,et al.  The TREC Spoken Document Retrieval Track: A Success Story , 2000, TREC.

[2]  John H. L. Hansen,et al.  Keyword recognition with phone confusion networks and phonological features based keyword threshold detection , 2010, 2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers.

[3]  Niko Brümmer,et al.  Application-independent evaluation of speaker detection , 2006, Comput. Speech Lang..

[4]  Richard M. Schwartz,et al.  White Listing and Score Normalization for Keyword Spotting of Noisy Speech , 2012, INTERSPEECH.

[5]  Andreas Stolcke,et al.  Improving Language Recognition with Multilingual Phone Recognition and Speaker Adaptation Transforms , 2010, Odyssey.

[6]  John H. L. Hansen,et al.  Environmental Sniffing: Noise Knowledge Estimation for Robust Speech Systems , 2003, IEEE Transactions on Audio, Speech, and Language Processing.

[7]  Arindam Mandal,et al.  Normalized amplitude modulation features for large vocabulary noise-robust speech recognition , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  Andreas Stolcke,et al.  The SRI/OGI 2006 spoken term detection system , 2007, INTERSPEECH.

[9]  M. Woodbury.  Information access , 2003 .

[10]  Andreas Stolcke,et al.  Effective Arabic Dialect Classification Using Diverse Phonotactic Models , 2011, INTERSPEECH.

[11]  John H. L. Hansen,et al.  Audio stream phrase recognition for a national gallery of the spoken word: "one small step" , 2000, INTERSPEECH.

[12]  Andreas Stolcke,et al.  Improving robustness of MLLR adaptation with speaker-clustered regression class trees , 2009, Comput. Speech Lang..

[13]  F ChenStanley,et al.  An Empirical Study of Smoothing Techniques for Language Modeling , 1996, ACL.

[14]  Kai Feng,et al.  The subspace Gaussian mixture model - A structured model for speech recognition , 2011, Comput. Speech Lang..

[15]  Daniel Povey,et al.  The Kaldi Speech Recognition Toolkit , 2011 .

[16]  Lukás Burget,et al.  A unified approach for audio characterization and its application to speaker recognition , 2012, Odyssey.

[17]  Kevin Walker,et al.  The RATS radio traffic collection system , 2012, Odyssey.

[18]  John H. L. Hansen,et al.  SPEECHFIND: spoken document retrieval for a national gallery of the spoken word , 2004, Proceedings of the 6th Nordic Signal Processing Symposium, 2004. NORSIG 2004..