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
전화 네트워크를 통해 전송되는 음성 신호는 주변 소음과 채널 왜곡으로 인해 간섭을 받는 경우가 많습니다. 본 논문에서는 채널 효과를 최소화하기 위해 XNUMX단계 바이어스 감산을 사용하는 새로운 프레임 종속 퍼지 채널 보상(FD-FCC) 방법을 제안합니다. 먼저, 모든 단어 모델 집합에 대한 최대 우도(ML) 추정을 통해 입력 발화와 가장 잘 일치하는 단어 모델을 선택합니다. 그런 다음 이 단어 모델을 기반으로 입력 발화와 선택한 모델 간의 셉스트럴 차이를 평균하여 혼합 편향 세트를 파생할 수 있습니다. 두 번째 단계에서는 단일 바이어스를 사용하는 대신 각 입력 프레임에 대해 프레임 종속 바이어스를 계산하여 입력 발언의 채널 변화를 균등화합니다. 이러한 프레임 종속 편향은 퍼지 소속 함수에 의해 가중치가 부여되는 혼합 편향의 볼록한 조합에 의해 달성됩니다. 실험 결과는 전화 음성 인식 시스템에 부가적인 배경 잡음이 포함되어 있어도 채널 효과가 효과적으로 제거될 수 있음을 보여줍니다.
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
Wei-Wen HUNG, Hsiao-Chuan WANG, "A Frame-Dependent Fuzzy Compensation Method for Speech Recognition over Time-Varying Telephone Channels" in IEICE TRANSACTIONS on Information,
vol. E82-D, no. 2, pp. 431-438, February 1999, doi: .
Abstract: Speech signals transmitted over telephone network often suffer from interference due to ambient noise and channel distortion. In this paper, a novel frame-dependent fuzzy channel compensation (FD-FCC) method employing two-stage bias subtraction is proposed to minimize the channel effect. First, through maximum likelihood (ML) estimation over the set of all word models, we choose the word model which is best matched with the input utterance. Then, based upon this word model, a set of mixture biases can be derived by averaging the cepstral differences between the input utterance and the chosen model. In the second stage, instead of using a single bias, a frame-dependent bias is calculated for each input frame to equalize the channel variations in the input utterance. This frame-dependent bias is achieved by the convex combination of those mixture biases which are weighted by a fuzzy membership function. Experimental results show that the channel effect can be effectively canceled even though the additive background noise is involved in a telephone speech recognition system.
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_2_431/_p
부
@ARTICLE{e82-d_2_431,
author={Wei-Wen HUNG, Hsiao-Chuan WANG, },
journal={IEICE TRANSACTIONS on Information},
title={A Frame-Dependent Fuzzy Compensation Method for Speech Recognition over Time-Varying Telephone Channels},
year={1999},
volume={E82-D},
number={2},
pages={431-438},
abstract={Speech signals transmitted over telephone network often suffer from interference due to ambient noise and channel distortion. In this paper, a novel frame-dependent fuzzy channel compensation (FD-FCC) method employing two-stage bias subtraction is proposed to minimize the channel effect. First, through maximum likelihood (ML) estimation over the set of all word models, we choose the word model which is best matched with the input utterance. Then, based upon this word model, a set of mixture biases can be derived by averaging the cepstral differences between the input utterance and the chosen model. In the second stage, instead of using a single bias, a frame-dependent bias is calculated for each input frame to equalize the channel variations in the input utterance. This frame-dependent bias is achieved by the convex combination of those mixture biases which are weighted by a fuzzy membership function. Experimental results show that the channel effect can be effectively canceled even though the additive background noise is involved in a telephone speech recognition system.},
keywords={},
doi={},
ISSN={},
month={February},}
부
TY - JOUR
TI - A Frame-Dependent Fuzzy Compensation Method for Speech Recognition over Time-Varying Telephone Channels
T2 - IEICE TRANSACTIONS on Information
SP - 431
EP - 438
AU - Wei-Wen HUNG
AU - Hsiao-Chuan WANG
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 1999
AB - Speech signals transmitted over telephone network often suffer from interference due to ambient noise and channel distortion. In this paper, a novel frame-dependent fuzzy channel compensation (FD-FCC) method employing two-stage bias subtraction is proposed to minimize the channel effect. First, through maximum likelihood (ML) estimation over the set of all word models, we choose the word model which is best matched with the input utterance. Then, based upon this word model, a set of mixture biases can be derived by averaging the cepstral differences between the input utterance and the chosen model. In the second stage, instead of using a single bias, a frame-dependent bias is calculated for each input frame to equalize the channel variations in the input utterance. This frame-dependent bias is achieved by the convex combination of those mixture biases which are weighted by a fuzzy membership function. Experimental results show that the channel effect can be effectively canceled even though the additive background noise is involved in a telephone speech recognition system.
ER -