In this paper, we propose a predictive block-constrained trellis-coded quantization (BC-TCQ) to quantize cepstral coefficients for distributed speech recognition. For prediction of the cepstral coefficients, the first order auto-regressive (AR) predictor is used. To quantize the prediction error signal effectively, we use the BC-TCQ. The quantization is compared to the split vector quantizers used in the ETSI standard, and is shown to lower cepstral distance and bit rates.
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
Sangwon KANG, Joonseok LEE, "Predictive Trellis-Coded Quantization of the Cepstral Coefficients for the Distributed Speech Recognition" in IEICE TRANSACTIONS on Communications,
vol. E90-B, no. 6, pp. 1570-1572, June 2007, doi: 10.1093/ietcom/e90-b.6.1570.
Abstract: In this paper, we propose a predictive block-constrained trellis-coded quantization (BC-TCQ) to quantize cepstral coefficients for distributed speech recognition. For prediction of the cepstral coefficients, the first order auto-regressive (AR) predictor is used. To quantize the prediction error signal effectively, we use the BC-TCQ. The quantization is compared to the split vector quantizers used in the ETSI standard, and is shown to lower cepstral distance and bit rates.
URL: https://global.ieice.org/en_transactions/communications/10.1093/ietcom/e90-b.6.1570/_p
Copy
@ARTICLE{e90-b_6_1570,
author={Sangwon KANG, Joonseok LEE, },
journal={IEICE TRANSACTIONS on Communications},
title={Predictive Trellis-Coded Quantization of the Cepstral Coefficients for the Distributed Speech Recognition},
year={2007},
volume={E90-B},
number={6},
pages={1570-1572},
abstract={In this paper, we propose a predictive block-constrained trellis-coded quantization (BC-TCQ) to quantize cepstral coefficients for distributed speech recognition. For prediction of the cepstral coefficients, the first order auto-regressive (AR) predictor is used. To quantize the prediction error signal effectively, we use the BC-TCQ. The quantization is compared to the split vector quantizers used in the ETSI standard, and is shown to lower cepstral distance and bit rates.},
keywords={},
doi={10.1093/ietcom/e90-b.6.1570},
ISSN={1745-1345},
month={June},}
Copy
TY - JOUR
TI - Predictive Trellis-Coded Quantization of the Cepstral Coefficients for the Distributed Speech Recognition
T2 - IEICE TRANSACTIONS on Communications
SP - 1570
EP - 1572
AU - Sangwon KANG
AU - Joonseok LEE
PY - 2007
DO - 10.1093/ietcom/e90-b.6.1570
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E90-B
IS - 6
JA - IEICE TRANSACTIONS on Communications
Y1 - June 2007
AB - In this paper, we propose a predictive block-constrained trellis-coded quantization (BC-TCQ) to quantize cepstral coefficients for distributed speech recognition. For prediction of the cepstral coefficients, the first order auto-regressive (AR) predictor is used. To quantize the prediction error signal effectively, we use the BC-TCQ. The quantization is compared to the split vector quantizers used in the ETSI standard, and is shown to lower cepstral distance and bit rates.
ER -