ATR Parallel Decoding Based Speech Recognition System Robust to Noise and Speaking Styles

Shigeki MATSUDA; Takatoshi JITSUHIRO; Konstantin MARKOV; Satoshi NAKAMURA

doi:10.1093/ietisy/e89-d.3.989

ATR Parallel Decoding Based Speech Recognition System Robust to Noise and Speaking Styles

Shigeki MATSUDA, Takatoshi JITSUHIRO, Konstantin MARKOV, Satoshi NAKAMURA

Full Text Views

0

Cite this

Summary :

In this paper, we describe a parallel decoding-based ASR system developed of ATR that is robust to noise type, SNR and speaking style. It is difficult to recognize speech affected by various factors, especially when an ASR system contains only a single acoustic model. One solution is to employ multiple acoustic models, one model for each different condition. Even though the robustness of each acoustic model is limited, the whole ASR system can handle various conditions appropriately. In our system, there are two recognition sub-systems which use different features such as MFCC and Differential MFCC (DMFCC). Each sub-system has several acoustic models depending on SNR, speaker gender and speaking style, and during recognition each acoustic model is adapted by fast noise adaptation. From each sub-system, one hypothesis is selected based on posterior probability. The final recognition result is obtained by combining the best hypotheses from the two sub-systems. On the AURORA-2J task used widely for the evaluation of noise robustness, our system achieved higher recognition performance than a system which contains only a single model. Also, our system was tested using normal and hyper-articulated speech contaminated by several background noises, and exhibited high robustness to noise and speaking styles.

Publication: IEICE TRANSACTIONS on Information Vol.E89-D No.3 pp.989-997

Publication Date: 2006/03/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e89-d.3.989

Type of Manuscript: Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)

Category: Speech Recognition

Cite this

Copy

Shigeki MATSUDA, Takatoshi JITSUHIRO, Konstantin MARKOV, Satoshi NAKAMURA, "ATR Parallel Decoding Based Speech Recognition System Robust to Noise and Speaking Styles" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 3, pp. 989-997, March 2006, doi: 10.1093/ietisy/e89-d.3.989.
Abstract: In this paper, we describe a parallel decoding-based ASR system developed of ATR that is robust to noise type, SNR and speaking style. It is difficult to recognize speech affected by various factors, especially when an ASR system contains only a single acoustic model. One solution is to employ multiple acoustic models, one model for each different condition. Even though the robustness of each acoustic model is limited, the whole ASR system can handle various conditions appropriately. In our system, there are two recognition sub-systems which use different features such as MFCC and Differential MFCC (DMFCC). Each sub-system has several acoustic models depending on SNR, speaker gender and speaking style, and during recognition each acoustic model is adapted by fast noise adaptation. From each sub-system, one hypothesis is selected based on posterior probability. The final recognition result is obtained by combining the best hypotheses from the two sub-systems. On the AURORA-2J task used widely for the evaluation of noise robustness, our system achieved higher recognition performance than a system which contains only a single model. Also, our system was tested using normal and hyper-articulated speech contaminated by several background noises, and exhibited high robustness to noise and speaking styles.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.3.989/_p

Copy

@ARTICLE{e89-d_3_989,
author={Shigeki MATSUDA, Takatoshi JITSUHIRO, Konstantin MARKOV, Satoshi NAKAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={ATR Parallel Decoding Based Speech Recognition System Robust to Noise and Speaking Styles},
year={2006},
volume={E89-D},
number={3},
pages={989-997},
abstract={In this paper, we describe a parallel decoding-based ASR system developed of ATR that is robust to noise type, SNR and speaking style. It is difficult to recognize speech affected by various factors, especially when an ASR system contains only a single acoustic model. One solution is to employ multiple acoustic models, one model for each different condition. Even though the robustness of each acoustic model is limited, the whole ASR system can handle various conditions appropriately. In our system, there are two recognition sub-systems which use different features such as MFCC and Differential MFCC (DMFCC). Each sub-system has several acoustic models depending on SNR, speaker gender and speaking style, and during recognition each acoustic model is adapted by fast noise adaptation. From each sub-system, one hypothesis is selected based on posterior probability. The final recognition result is obtained by combining the best hypotheses from the two sub-systems. On the AURORA-2J task used widely for the evaluation of noise robustness, our system achieved higher recognition performance than a system which contains only a single model. Also, our system was tested using normal and hyper-articulated speech contaminated by several background noises, and exhibited high robustness to noise and speaking styles.},
keywords={},
doi={10.1093/ietisy/e89-d.3.989},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - ATR Parallel Decoding Based Speech Recognition System Robust to Noise and Speaking Styles
T2 - IEICE TRANSACTIONS on Information
SP - 989
EP - 997
AU - Shigeki MATSUDA
AU - Takatoshi JITSUHIRO
AU - Konstantin MARKOV
AU - Satoshi NAKAMURA
PY - 2006
DO - 10.1093/ietisy/e89-d.3.989
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2006
AB - In this paper, we describe a parallel decoding-based ASR system developed of ATR that is robust to noise type, SNR and speaking style. It is difficult to recognize speech affected by various factors, especially when an ASR system contains only a single acoustic model. One solution is to employ multiple acoustic models, one model for each different condition. Even though the robustness of each acoustic model is limited, the whole ASR system can handle various conditions appropriately. In our system, there are two recognition sub-systems which use different features such as MFCC and Differential MFCC (DMFCC). Each sub-system has several acoustic models depending on SNR, speaker gender and speaking style, and during recognition each acoustic model is adapted by fast noise adaptation. From each sub-system, one hypothesis is selected based on posterior probability. The final recognition result is obtained by combining the best hypotheses from the two sub-systems. On the AURORA-2J task used widely for the evaluation of noise robustness, our system achieved higher recognition performance than a system which contains only a single model. Also, our system was tested using normal and hyper-articulated speech contaminated by several background noises, and exhibited high robustness to noise and speaking styles.
ER -