The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
입력 음성의 관찰 확률을 최대화하는 화자 적응 기법을 제안한다. 반연속적 은닉 마르코프 모델(SCHMM) 음성 인식기에 적용됩니다. 제안된 알고리즘은 적응 음성 데이터의 특징이 최대 관찰 확률을 달성할 수 있도록 기울기 탐색 기법을 통해 평균 μ와 공분산 Σ를 반복적으로 적응시킵니다. 혼합 계수와 상태 전이 확률은 모델 보간 방식에 의해 조정됩니다. 이 방식의 가장 큰 장점은 SCHMM의 모든 상태에 공통적인 평균과 분산이 SCHMM의 다른 매개변수와 독립적으로 적용된다는 것입니다. 특히 참조 모델과 새 스피커 사이에 음향 불일치가 큰 경우 빠르고 정확한 적응이 가능합니다. 또한, 코드북을 사용하는 다른 분야에도 이 방식이 적용될 가능성이 있다. 제안된 적응 알고리즘은 남성 화자 의존적, 여성 화자 의존적, 화자 독립적 인식기에 의해 평가되었다. 격리된 단어 인식에 대한 실험 결과, 제안한 적응 알고리즘은 남성 화자 의존적 인식기에서 평균 46.03%, 여성 화자 의존적 인식기에서는 52.18%, 화자 독립적 인식기에서는 9.84%의 평균 향상을 보였다.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Tae-Young YANG, Chungyong LEE, Dae-Hee YOUN, "Speaker Adaptation Based on a Maximum Observation Probability Criterion" in IEICE TRANSACTIONS on Information,
vol. E84-D, no. 2, pp. 286-288, February 2001, doi: .
Abstract: A speaker adaptation technique that maximizes the observation probability of an input speech is proposed. It is applied to semi-continuous hidden Markov model (SCHMM) speech recognizers. The proposed algorithm adapts the mean µ and the covariance Σ iteratively by the gradient search technique so that the features of the adaptation speech data could achieve maximum observation probabilities. The mixture coefficients and the state transition probabilities are adapted by the model interpolation scheme. The main advantage of this scheme is that the means and the variances, which are common to all states in SCHMM, are adapted independently from the other parameters of SCHMM. It allows fast and precise adaptation especially when there is a large acoustic mismatch between the reference model and a new speaker. Also, it is possible that this scheme could be adopted to other areas which use codebook. The proposed adaptation algorithm was evaluated by a male speaker-dependent, a female speaker-dependent, and a speaker-independent recognizers. The experimental results on the isolated word recognition showed that the proposed adaptation algorithm achieved 46.03% average enhancement in the male speaker-dependent recognizer, 52.18% in the female speaker-dependent recognizer, and 9.84% in the speaker-independent recognizer.
URL: https://global.ieice.org/en_transactions/information/10.1587/e84-d_2_286/_p
부
@ARTICLE{e84-d_2_286,
author={Tae-Young YANG, Chungyong LEE, Dae-Hee YOUN, },
journal={IEICE TRANSACTIONS on Information},
title={Speaker Adaptation Based on a Maximum Observation Probability Criterion},
year={2001},
volume={E84-D},
number={2},
pages={286-288},
abstract={A speaker adaptation technique that maximizes the observation probability of an input speech is proposed. It is applied to semi-continuous hidden Markov model (SCHMM) speech recognizers. The proposed algorithm adapts the mean µ and the covariance Σ iteratively by the gradient search technique so that the features of the adaptation speech data could achieve maximum observation probabilities. The mixture coefficients and the state transition probabilities are adapted by the model interpolation scheme. The main advantage of this scheme is that the means and the variances, which are common to all states in SCHMM, are adapted independently from the other parameters of SCHMM. It allows fast and precise adaptation especially when there is a large acoustic mismatch between the reference model and a new speaker. Also, it is possible that this scheme could be adopted to other areas which use codebook. The proposed adaptation algorithm was evaluated by a male speaker-dependent, a female speaker-dependent, and a speaker-independent recognizers. The experimental results on the isolated word recognition showed that the proposed adaptation algorithm achieved 46.03% average enhancement in the male speaker-dependent recognizer, 52.18% in the female speaker-dependent recognizer, and 9.84% in the speaker-independent recognizer.},
keywords={},
doi={},
ISSN={},
month={February},}
부
TY - JOUR
TI - Speaker Adaptation Based on a Maximum Observation Probability Criterion
T2 - IEICE TRANSACTIONS on Information
SP - 286
EP - 288
AU - Tae-Young YANG
AU - Chungyong LEE
AU - Dae-Hee YOUN
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E84-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2001
AB - A speaker adaptation technique that maximizes the observation probability of an input speech is proposed. It is applied to semi-continuous hidden Markov model (SCHMM) speech recognizers. The proposed algorithm adapts the mean µ and the covariance Σ iteratively by the gradient search technique so that the features of the adaptation speech data could achieve maximum observation probabilities. The mixture coefficients and the state transition probabilities are adapted by the model interpolation scheme. The main advantage of this scheme is that the means and the variances, which are common to all states in SCHMM, are adapted independently from the other parameters of SCHMM. It allows fast and precise adaptation especially when there is a large acoustic mismatch between the reference model and a new speaker. Also, it is possible that this scheme could be adopted to other areas which use codebook. The proposed adaptation algorithm was evaluated by a male speaker-dependent, a female speaker-dependent, and a speaker-independent recognizers. The experimental results on the isolated word recognition showed that the proposed adaptation algorithm achieved 46.03% average enhancement in the male speaker-dependent recognizer, 52.18% in the female speaker-dependent recognizer, and 9.84% in the speaker-independent recognizer.
ER -