%Aigaion2 BibTeX export from Idiap Publications %Friday 11 October 2024 02:13:28 AM @INPROCEEDINGS{pinto:SSCS:2008, author = {Pinto, Joel Praveen and Szoke, Igor and Prasanna, S. R. Mahadeva and Hermansky, Hynek}, projects = {Idiap}, title = {{Fast Approximate Spoken Term Detection from Sequence of Phonemes}}, booktitle = {{Workshop on Searching Spontaneous Conversational Speech at SIGIR}}, year = {2008}, note = {IDIAP-RR 08-45}, crossref = {pinto:rr08-45}, abstract = {We investigate the detection of spoken terms in conversational speech using phoneme recognition with the objective of achieving smaller index size as well as faster search speed. Speech is processed and indexed as a sequence of one best phoneme sequence. We propose the use of a probabilistic pronunciation model for the search term to compensate for the errors in the recognition of phonemes. This model is derived using the pronunciation of the word and the phoneme confusion matrix. Experiments are performed on the conversational telephone speech database distributed by NIST for the 2006 spoken term detection. We achieve about 1500 times smaller index size and 14 times faster search speed compared to the state-of-the-art system using phoneme lattice at the cost of relatively lower detection performance.}, pdf = {https://publications.idiap.ch/attachments/papers/2008/pinto-SSCS-2008.pdf}, postscript = {ftp://ftp.idiap.ch/pub/papers/2008/pinto-SSCS-2008.ps.gz}, ipdmembership={speech}, } crossreferenced publications: @TECHREPORT{pinto:rr08-45, author = {Pinto, Joel Praveen and Szoke, Igor and Prasanna, S. R. Mahadeva and Hermansky, Hynek}, projects = {Idiap}, title = {{Fast Approximate Spoken Term Detection from Sequence of Phonemes}}, type = {Idiap-RR}, number = {Idiap-RR-45-2008}, year = {2008}, institution = {IDIAP}, note = {Submitted for publication}, abstract = {We investigate the detection of spoken terms in conversational speech using phoneme recognition with the objective of achieving smaller index size as well as faster search speed. Speech is processed and indexed as a sequence of one best phoneme sequence. We propose the use of a probabilistic pronunciation model for the search term to compensate for the errors in the recognition of phonemes. This model is derived using the pronunciation of the word and the phoneme confusion matrix. Experiments are performed on the conversational telephone speech database distributed by NIST for the 2006 spoken term detection. We achieve about 1500 times smaller index size and 14 times faster search speed compared to the state-of-the-art system using phoneme lattice at the cost of relatively lower detection performance.}, pdf = {https://publications.idiap.ch/attachments/reports/2008/pinto-idiap-rr-08-45.pdf}, postscript = {ftp://ftp.idiap.ch/pub/reports/2008/pinto-idiap-rr-08-45.ps.gz}, ipdmembership={speech}, }