{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,5]],"date-time":"2022-04-05T10:25:25Z","timestamp":1649154325908},"reference-count":0,"publisher":"World Scientific Pub Co Pte Lt","issue":"04","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[1993,8]]},"abstract":"<jats:p> Up till recently, state-of-the-art, large vocabulary, continuous speech recognition (CSR) had employed hidden Markov modeling (HMM) to model speech sounds. In an attempt to improve over HMM we developed a hybrid system that integrates HMM technology with neural networks. <\/jats:p><jats:p> We present the concept of a Segmental Neural Net (SNN) for phonetic modeling in CSR. By taking into account all the frames of a phonetic segment simultaneously, the SNN overcomes the well-known conditional-independence limitation of HMMs. We have developed a novel hybrid SNN\/HMM system that combines the advantages of SNNs and HMMs using a multiple hypothesis (or N-best) paradigm. In this system, we generate likely phonetic segmentations from the HMM N-best list of word sequences, which are scored by the SNN. The HMM and SNN scores are then combined to optimize performance. <\/jats:p><jats:p> In several speaker-independent, 1000-word CSR tests, the error rate for the hybrid system dropped 20% from that of a state-of-the-art HMM system alone. <\/jats:p>","DOI":"10.1142\/s0218001493000480","type":"journal-article","created":{"date-parts":[[2004,11,22]],"date-time":"2004-11-22T22:29:30Z","timestamp":1101162570000},"page":"949-963","source":"Crossref","is-referenced-by-count":5,"title":["A HYBRID CONTINUOUS SPEECH RECOGNITION SYSTEM USING SEGMENTAL NEURAL NETS WITH HIDDEN MARKOV MODELS"],"prefix":"10.1142","volume":"07","author":[{"given":"G.","family":"ZAVALIAGKOS","sequence":"first","affiliation":[{"name":"Northeastern University, Boston, MA 02115, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"AUSTIN","sequence":"additional","affiliation":[{"name":"BBN Systems and Technologies, Cambridge, MA 02138, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J.","family":"MAKHOUL","sequence":"additional","affiliation":[{"name":"BBN Systems and Technologies, Cambridge, MA 02138, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"SCHWARTZ","sequence":"additional","affiliation":[{"name":"BBN Systems and Technologies, Cambridge, MA 02138, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2011,11,21]]},"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001493000480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T22:13:00Z","timestamp":1565129580000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0218001493000480"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1993,8]]},"references-count":0,"journal-issue":{"issue":"04","published-online":{"date-parts":[[2011,11,21]]},"published-print":{"date-parts":[[1993,8]]}},"alternative-id":["10.1142\/S0218001493000480"],"URL":"https:\/\/doi.org\/10.1142\/s0218001493000480","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"value":"0218-0014","type":"print"},{"value":"1793-6381","type":"electronic"}],"subject":[],"published":{"date-parts":[[1993,8]]}}}