Effects of Word Confusion Networks on Voice Search

Mobile voice-enabled search is emerging as one of the most popular applications abetted by the exponential growth in the number of mobile devices. The automatic speech recognition (ASR) output of the voice query is parsed into several fields. Search is then performed on a text corpus or a database. In order to improve the robustness of the query parser to noise in the ASR output, in this paper, we investigate two different methods to query parsing. Both methods exploit multiple hypotheses from ASR, in the form of word confusion networks, in order to achieve tighter coupling between ASR and query parsing and improved accuracy of the query parser. We also investigate the results of this improvement on search accuracy. Word confusion-network based query parsing outperforms ASR 1-best based query-parsing by 2.7% absolute and the search performance improves by 1.8% absolute on one of our data sets.

[1]  Richard M. Schwartz,et al.  A scalable architecture for Directory Assistance automation , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Otis Gospodnetic,et al.  Lucene in Action (In Action series) , 2004 .

[3]  Frédéric Béchet,et al.  Robust Named Entity Extraction from Large Spoken Archives , 2005, HLT/EMNLP.

[4]  Geoffrey Zweig,et al.  Automated directory assistance system - from theory to practice , 2007, INTERSPEECH.

[5]  Dong Yu,et al.  An introduction to voice search , 2008, IEEE Signal Processing Magazine.

[6]  Alexander Dekhtyar,et al.  Information Retrieval , 2018, Lecture Notes in Computer Science.

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

[8]  Ralph Weischedel,et al.  NAMED ENTITY EXTRACTION FROM SPEECH , 1998 .

[9]  Fuchun Peng,et al.  Unsupervised query segmentation using generative language models and wikipedia , 2008, WWW.

[10]  Peter Thanisch,et al.  Natural language interfaces to databases – an introduction , 1995, Natural Language Engineering.

[11]  Brian Roark,et al.  A generalized construction of integrated speech recognition transducers , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.