Presentation 1995/11/16
On detection of unregistered-words using phoneme cluster models
Hiroyuki SAKAMOTO, Shoichi MATSUNAGA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a speech recognition strategy to deal with utterances having unregistered words. The strategy integrates unregistered-word detection using phoneme cluster Hidden Markov Models (HMMs) and registered-word recognition using phoneme HMMs. These phoneme cluster models are designed to minimize both the increase in processing for unregistered words and the decrease in the recognition performance for registered words. A further goal is to maximize the detection performance of unregistered words. In sentence recognition experiments using this unregistered-word processing, the proposed cluster models that achieved the best word accuracy of 70.3%, compared with 58.1% for sentence recognition without this processing. The processing using the cluster models is the half computation and perform as well as phoneme models. We confirmed the effectiveness of this strategy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Continuous Speech Recognition / Phoneme C1uster Model / N-grams / Unregistered-word
Paper # SP95-76
Date of Issue

Conference Information
Committee SP
Conference Date 1995/11/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On detection of unregistered-words using phoneme cluster models
Sub Title (in English)
Keyword(1) Continuous Speech Recognition
Keyword(2) Phoneme C1uster Model
Keyword(3) N-grams
Keyword(4) Unregistered-word
1st Author's Name Hiroyuki SAKAMOTO
1st Author's Affiliation ATR Interpreting Telecommunications Research Laboratories()
2nd Author's Name Shoichi MATSUNAGA
2nd Author's Affiliation ATR Interpreting Telecommunications Research Laboratories
Date 1995/11/16
Paper # SP95-76
Volume (vol) vol.95
Number (no) 355
Page pp.pp.-
#Pages 7
Date of Issue