For reducing requirement of large memory and minimizing computation complexity in a large-vocabulary continuous speech recognition system, speech segmentation plays an important role in speech recognition systems. In this paper, we formulate the speech segmentation as a two-phase problem. Phase 1 (frame labeling) involves labeling frames of speech data. Frames are classified into three types: (1) silence, (2) consonant and (3) vowel according to two segmentation features. In phase 2 (syllabic unit segmentation) we apply the concept of transition states to segment continuous speech data into syllabic units based on the labeled frames. The novel class of hyperrectangular composite neural networks (HRCNNs) is used to cluster frames. The HRCNNs integrate the rule-based approach and neural network paradigms, therefore, this special hybrid system may neutralize the disadvantages of each alternative. The parameters of the trained HRCNNs are utilized to extract both crisp and fuzzy classification rules. In our experiments, a database containing continuous reading-rate Mandarin speech recorded from newscast was utilized to illustrate the performance of the proposed speaker independent speech segmentation system. The effectiveness of the proposed segmentation system is confirmed by the experimental results.
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.
Copy
Ching-Tang HSIEH, Mu-Chun SU, Chih-Hsu HSU, "Continuous Speech Segmentation Based on a Self-Learning Neuro-Fuzzy System" in IEICE TRANSACTIONS on Fundamentals,
vol. E79-A, no. 8, pp. 1180-1187, August 1996, doi: .
Abstract: For reducing requirement of large memory and minimizing computation complexity in a large-vocabulary continuous speech recognition system, speech segmentation plays an important role in speech recognition systems. In this paper, we formulate the speech segmentation as a two-phase problem. Phase 1 (frame labeling) involves labeling frames of speech data. Frames are classified into three types: (1) silence, (2) consonant and (3) vowel according to two segmentation features. In phase 2 (syllabic unit segmentation) we apply the concept of transition states to segment continuous speech data into syllabic units based on the labeled frames. The novel class of hyperrectangular composite neural networks (HRCNNs) is used to cluster frames. The HRCNNs integrate the rule-based approach and neural network paradigms, therefore, this special hybrid system may neutralize the disadvantages of each alternative. The parameters of the trained HRCNNs are utilized to extract both crisp and fuzzy classification rules. In our experiments, a database containing continuous reading-rate Mandarin speech recorded from newscast was utilized to illustrate the performance of the proposed speaker independent speech segmentation system. The effectiveness of the proposed segmentation system is confirmed by the experimental results.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e79-a_8_1180/_p
Copy
@ARTICLE{e79-a_8_1180,
author={Ching-Tang HSIEH, Mu-Chun SU, Chih-Hsu HSU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Continuous Speech Segmentation Based on a Self-Learning Neuro-Fuzzy System},
year={1996},
volume={E79-A},
number={8},
pages={1180-1187},
abstract={For reducing requirement of large memory and minimizing computation complexity in a large-vocabulary continuous speech recognition system, speech segmentation plays an important role in speech recognition systems. In this paper, we formulate the speech segmentation as a two-phase problem. Phase 1 (frame labeling) involves labeling frames of speech data. Frames are classified into three types: (1) silence, (2) consonant and (3) vowel according to two segmentation features. In phase 2 (syllabic unit segmentation) we apply the concept of transition states to segment continuous speech data into syllabic units based on the labeled frames. The novel class of hyperrectangular composite neural networks (HRCNNs) is used to cluster frames. The HRCNNs integrate the rule-based approach and neural network paradigms, therefore, this special hybrid system may neutralize the disadvantages of each alternative. The parameters of the trained HRCNNs are utilized to extract both crisp and fuzzy classification rules. In our experiments, a database containing continuous reading-rate Mandarin speech recorded from newscast was utilized to illustrate the performance of the proposed speaker independent speech segmentation system. The effectiveness of the proposed segmentation system is confirmed by the experimental results.},
keywords={},
doi={},
ISSN={},
month={August},}
Copy
TY - JOUR
TI - Continuous Speech Segmentation Based on a Self-Learning Neuro-Fuzzy System
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1180
EP - 1187
AU - Ching-Tang HSIEH
AU - Mu-Chun SU
AU - Chih-Hsu HSU
PY - 1996
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E79-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 1996
AB - For reducing requirement of large memory and minimizing computation complexity in a large-vocabulary continuous speech recognition system, speech segmentation plays an important role in speech recognition systems. In this paper, we formulate the speech segmentation as a two-phase problem. Phase 1 (frame labeling) involves labeling frames of speech data. Frames are classified into three types: (1) silence, (2) consonant and (3) vowel according to two segmentation features. In phase 2 (syllabic unit segmentation) we apply the concept of transition states to segment continuous speech data into syllabic units based on the labeled frames. The novel class of hyperrectangular composite neural networks (HRCNNs) is used to cluster frames. The HRCNNs integrate the rule-based approach and neural network paradigms, therefore, this special hybrid system may neutralize the disadvantages of each alternative. The parameters of the trained HRCNNs are utilized to extract both crisp and fuzzy classification rules. In our experiments, a database containing continuous reading-rate Mandarin speech recorded from newscast was utilized to illustrate the performance of the proposed speaker independent speech segmentation system. The effectiveness of the proposed segmentation system is confirmed by the experimental results.
ER -