Indexing and searching audio using text indexers

Details Indexing and searching audio using text indexers Indexing and searching audio using text indexers

2007-12-07

2011-11-15

Al Hashemi, Sana (Department: 2156)

Data processing: database and file management or data structures

Database and file access

Query optimization

C707S706000, C707S708000, C707S723000, C707S728000

Reexamination Certificate

active

08060494

ABSTRACT:
A full-text lattice indexing and searching system and method for indexing word lattices using a text indexer to enable enhance searching of audio content. The system and method utilize a Time-Anchored Lattice Expansion (TALE) method that represents word lattices such that they can be indexed with existing text indexers with little or no modification. Embodiments of system and method include an indexing module for generating and indexing word lattices based on audio content and a searching module for allowing searching of a full-text index containing indexed word lattices. The indexing module includes a custom IFilter and a custom Wordbreaker. Embodiments of the searching module include an ExpandQuery function for decorating an input query and a custom Stemmer. Embodiments of the searching module also include a GenerateSnippets module that extracts information from the indexed word lattices to enable the creation of clickable snippets.

REFERENCES:
patent: 6345253 (2002-02-01), Viswanathan
patent: 6877001 (2005-04-01), Wolf et al.
patent: 7110664 (2006-09-01), Yogeshwar et al.
patent: 7257533 (2007-08-01), Charlesworth et al.
patent: 7272558 (2007-09-01), Soucy et al.
patent: 7272562 (2007-09-01), Olorenshaw et al.
patent: 7562010 (2009-07-01), Gretter et al.
patent: 2003/0171926 (2003-09-01), Suresh et al.
patent: 2004/0199494 (2004-10-01), Bhatt
patent: 2006/0116997 (2006-06-01), Yu et al.
patent: 2007/0053513 (2007-03-01), Hoffberg
patent: 2007/0106509 (2007-05-01), Acero et al.
patent: 2007/0106685 (2007-05-01), Houh et al.
patent: 2007/0112855 (2007-05-01), Ban et al.
patent: 2007/0143110 (2007-06-01), Acero et al.
patent: 1630705 (2006-10-01), None
International Search Report, Application No. PCT/US2008/085779, completed Mar. 31, 2009, received Mar. 31, 2009.
Brin, et al., “The Anatomy of a Large-Scale Hypertextual Web Search Engine”, Date: 1998, pp. 107-117.
Chelba, et al., “Soft Indexing of Speech Content for Search in Spoken Documents”, Date: Jul. 2007, vol. 21, Issued: 3, pp. 458-478.
Chelba, et al., “Position Specific Posterior Lattices for Indexing Speech”, Proceedings of the ACL, Date: 2005, pp. 1-8.
Evermann, et al., “Development of the 2004 CU-HTK English CTS Systems Using More Than Two Thousand Hours of Data”, Date: 2004, pp. 1-7.
Glass, et al., “Analysis and Processing of Lecture Audio data: Preliminary Investigation”, Proceedings of the HLTNAACL' 2004 Workshop: Interdisciplinary Approaches to Speech Indexing and Retrieval, Boston, Date: 2004, pp. 1-4.
Padmanabhan, et al., “Automatic Speech Recognition Performance on a Voicemail Transcription Task”, IEEE Transactions on Speech and Audio Processing, Date: 2002, vol. 10, Issue: 7, pp. 433-442.
Saraclar, et al., “Lattice-Based Search for Spoken Utterance Retrieval”, Proceeding of the HLT, Date: 2004, pp. 1-8.
Silverstein, et al., “Analysis of a Very Large Web Search Engine Query Log”, ACM SIGIR Forum, Date: 1999, vol. 33, Issue: 1, pp. 6-12.
Wessel, et al., “Using Posterior Word Probabilities for Improved Speech Recognition”, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP, Date: 2000, vol. 3, pp. 1587-1590.
Yu, et al., “A Hidden-State Maximum Entropy Model for Word Confidence Estimation”, In Proceedings of the ICASSP'2007, Date: Apr. 15-20, 2007, vol. 4, pp. IV-785-IV-788.
Yu, et al., “A Hybrid Word / Phoneme-Based Approach for Improved Vocabulary-Independent Search in Spontaneous Speech”, Proceedings of the ICLSP, Date: 2004, pp. 1-4.
Yu, et al., “Vocabulary-Independent Indexing of Spontaneous Speech”, IEEE Transactions on Speech and Audio Processing, Date: Sep. 2005, vol. 13, Issue: 5, pp. 635-643.
Zhou, et al., “Towards Spoken-Document Retrieval for the Internet: Lattice Indexing for Large-Scale Web-Search Architectures”, Proceedings of the HLT, Date: 2006, pp. 415-422, Association for Computational Linguistics, NJ, USA.
Burget, L., J. Cernocký, M. Fap{hacek over (s)}o, M. Karafiát, P. Matejka, P. Schwarz, P. Smr{hacek over (z)} and I. Szöke, Indexing and search methods for spoken documents, Proc. of the Ninth Int'l, Conf. on Text, Speech and Dialogue, 2006, pp. 351-358, vol. 4188, Springer Berlin / Heidelberg, Berlin, Germany.
Chelba, C., A. Acero, Speech Ogle: Indexing uncertainty for spoken document search, Proc. of the ACL 2005 on Interactive Poster and Demonstration Sessions, Jun. 25-30, 2005, pp. 41-44, ACM, Ann Arbor, Michigan.
Garofolo J., J. Lard, E. Voorhees, 2000 TREC-9 Spoken document retrieval track, National Institute of Standards and Technology, Information Technology Laboratory, Sep. 6, 2001, available at http://trec.nist.gov/pubs/trec9/sdrt9—slides/sld001.htm.
L. Mangu, E. Brill and A. Stolcke, Finding consensus in speech recognition: Word error minimization and other applications of confusion networks, Computer, Speech and Language, Oct. 2000, vol. 14 No. 4, pp. 373-400, Elsevier.
Olsson, J. S., Wintrode, J., Lee, M., Fast unconstrained audio search in numerous human languages, IEEE Int'l Conf. on Acoustics, Speech and Signal Processing, Apr. 15-20, 2007, pp. 77-80, vol. 4, IEEE, Honolulu, HI.
Saraclar, M., R. Sproat, Lattice-based search for spoken utterance retrieval, Proceedings of the Human Language Tech. Conf. of the North American Association for Computational Linguistics, 2004, pp. 129-136, Boston, MA.

Affiliated with

Also associated with

Rating

Indexing and searching audio using text indexers does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Indexing and searching audio using text indexers, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Indexing and searching audio using text indexers will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4278201