Comparing decoding strategies for subword-based keyword spotting in low-resourced languages

For languages with limited training resources, out-ofvocabulary (OOV) words are a significant problem, both for transcription and keyword spotting. This paper investigates the use of subword lexical units for keyword spotting. Three strategies for using the sub-word units are explored: 1) converting word-based lattices to subword lattices after decoding, 2) performing a separate decoding for each subword type, and 3) a single decoding using all possible subword units. In these experiments, the best performance is achieved by carrying out a separate decoding for each subword type. Further gains are attained through system combination. We also find that ignoring word boundaries improves the detection of OOV keywords without significantly impacting in-vocabulary keyword detection. Results are presented on four languages from the IARPA Babel Program (Haitian Creole, Assamese, Bengali, and Zulu).

[1]  Mari Ostendorf,et al.  Subword-based modeling for handling OOV words inkeyword spotting , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Nelson Morgan,et al.  The TAO of ATWV: Probing the mysteries of keyword search performance , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[3]  Martin Karafiát,et al.  Semi-supervised bootstrapping approach for neural network feature extractor training , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[4]  Arindam Mandal,et al.  Discriminatively trained phoneme confusion model for keyword spotting , 2012, INTERSPEECH.

[5]  Igor Sz.  SUB-WORD MODELING OF OUT OF VOCABULARY WORDS IN SPOKEN TERM DETECTION , 2008 .

[6]  Michael Picheny,et al.  Improvements in phone based audio search via constrained match with high order confusion estimates , 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

[7]  Jonathan G. Fiscus,et al.  Results of the 2006 Spoken Term Detection Evaluation , 2006 .

[8]  Richard M. Schwartz,et al.  Score normalization and system combination for improved keyword spotting , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[9]  Olivier Siohan,et al.  Fast vocabulary-independent audio search using path-based graph indexing , 2005, INTERSPEECH.

[10]  Ebru Arisoy,et al.  Unlimited vocabulary speech recognition for agglutinative languages , 2006, NAACL.

[11]  Jean-Luc Gauvain,et al.  The LIMSI Broadcast News transcription system , 2002, Speech Commun..

[12]  Jean-Luc Gauvain,et al.  Cross-word sub-word units for low-resource keyword spotting , 2014, SLTU.

[13]  Richard M. Schwartz,et al.  The 2013 BBN Vietnamese telephone speech keyword spotting system , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[14]  Owen Kimball,et al.  Subword speech recognition for detection of unseen words , 2012, INTERSPEECH.

[15]  Jean-Luc Gauvain,et al.  Developing STT and KWS systems using limited language resources , 2014, INTERSPEECH.

[16]  Mikko Kurimo,et al.  Morfessor 2.0: Python Implementation and Extensions for Morfessor Baseline , 2013 .

[17]  Sanjeev Khudanpur,et al.  Using proxies for OOV keywords in the keyword search task , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[18]  Richard Sproat,et al.  Lattice-Based Search for Spoken Utterance Retrieval , 2004, NAACL.

[19]  Richard M. Schwartz,et al.  Normalizationofphonetic keyword search scores , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[20]  Spyridon Matsoukas,et al.  Developing a Speech Activity Detection System for the DARPA RATS Program , 2012, INTERSPEECH.

[21]  Andreas Stolcke,et al.  Finding consensus in speech recognition: word error minimization and other applications of confusion networks , 2000, Comput. Speech Lang..