This paper proposes gain relaxation in signal enhancement designed for speech recognition. Gain relaxation selectively applies softer enhancement of a target signal to eliminate potential degradation in speech recognition caused by small undesirable distortion in the target signal components. The softer enhancement is a solution to overlooked performance degradation in signal enhancement combined with speech recognition which is encountered in commercial products with an unaware small local noise source. Evaluation of directional interference suppression with signals recorded by a commercial PC (personal computer) demonstrates that signal enhancement over the input is achieved without sacrificing the performance for clean speech.
Ryoji MIYAHARA
NEC Platforms
Akihiko SUGIYAMA
NEC Corporation,Tokyo Metropolitan University
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
Ryoji MIYAHARA, Akihiko SUGIYAMA, "Gain Relaxation: A Solution to Overlooked Performance Degradation in Speech Recognition with Signal Enhancement" in IEICE TRANSACTIONS on Fundamentals,
vol. E101-A, no. 11, pp. 1832-1840, November 2018, doi: 10.1587/transfun.E101.A.1832.
Abstract: This paper proposes gain relaxation in signal enhancement designed for speech recognition. Gain relaxation selectively applies softer enhancement of a target signal to eliminate potential degradation in speech recognition caused by small undesirable distortion in the target signal components. The softer enhancement is a solution to overlooked performance degradation in signal enhancement combined with speech recognition which is encountered in commercial products with an unaware small local noise source. Evaluation of directional interference suppression with signals recorded by a commercial PC (personal computer) demonstrates that signal enhancement over the input is achieved without sacrificing the performance for clean speech.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E101.A.1832/_p
Copy
@ARTICLE{e101-a_11_1832,
author={Ryoji MIYAHARA, Akihiko SUGIYAMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Gain Relaxation: A Solution to Overlooked Performance Degradation in Speech Recognition with Signal Enhancement},
year={2018},
volume={E101-A},
number={11},
pages={1832-1840},
abstract={This paper proposes gain relaxation in signal enhancement designed for speech recognition. Gain relaxation selectively applies softer enhancement of a target signal to eliminate potential degradation in speech recognition caused by small undesirable distortion in the target signal components. The softer enhancement is a solution to overlooked performance degradation in signal enhancement combined with speech recognition which is encountered in commercial products with an unaware small local noise source. Evaluation of directional interference suppression with signals recorded by a commercial PC (personal computer) demonstrates that signal enhancement over the input is achieved without sacrificing the performance for clean speech.},
keywords={},
doi={10.1587/transfun.E101.A.1832},
ISSN={1745-1337},
month={November},}
Copy
TY - JOUR
TI - Gain Relaxation: A Solution to Overlooked Performance Degradation in Speech Recognition with Signal Enhancement
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1832
EP - 1840
AU - Ryoji MIYAHARA
AU - Akihiko SUGIYAMA
PY - 2018
DO - 10.1587/transfun.E101.A.1832
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E101-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2018
AB - This paper proposes gain relaxation in signal enhancement designed for speech recognition. Gain relaxation selectively applies softer enhancement of a target signal to eliminate potential degradation in speech recognition caused by small undesirable distortion in the target signal components. The softer enhancement is a solution to overlooked performance degradation in signal enhancement combined with speech recognition which is encountered in commercial products with an unaware small local noise source. Evaluation of directional interference suppression with signals recorded by a commercial PC (personal computer) demonstrates that signal enhancement over the input is achieved without sacrificing the performance for clean speech.
ER -