An FFT-Based Companding Front End for Noise-Robust Automatic Speech Recognition

被引：4

作者：

Raj, Bhiksha ^{[1
]}

Turicchia, Lorenzo ^{[2
]}

Schmidt-Nielsen, Bent ^{[1
]}

Sarpeshkar, Rahul ^{[2
]}

机构：

[1] MERL, Cambridge, MA 02139 USA

[2] MIT, Cambridge, MA 02139 USA

来源：

EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING | 2007年 / 2007卷 / 1期

关键词：

Error Rate; Acoustics; Recognition Task; Recognition Performance; Auditory System;

D O I：

10.1155/2007/65420

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

We describe an FFT-based companding algorithm for preprocessing speech before recognition. The algorithm mimics tone-to-tone suppression and masking in the auditory system to improve automatic speech recognition performance in noise. Moreover, it is also very computationally efficient and suited to digital implementations due to its use of the FFT. In an automotive digits recognition task with the CU-Move database recorded in real environmental noise, the algorithm improves the relative word error by 12.5% at -5 dB signal-to-noise ratio (SNR) and by 6.2% across all SNRs (-5 dB SNR to +15 dB SNR). In the Aurora-2 database recorded with artificially added noise in several environments, the algorithm improves the relative word error rate in almost all situations. Copyright (C) 2007 Bhiksha Raj et al.

引用

页数：13

共 50 条

[1] An FFT-Based Companding Front End for Noise-Robust Automatic Speech Recognition
Bhiksha Raj
Lorenzo Turicchia
Bent Schmidt-Nielsen
Rahul Sarpeshkar
[J]. EURASIP Journal on Audio, Speech, and Music Processing, 2007
[2] A companding front end for noise-robust automatic speech recognition
Guinness, J
Raj, B
Schmidt-Nielsen, B
Turicchia, L
Sarpeshkar, R
[J]. 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 249 - 252
[3] A noise-robust FFT-based spectrum for audio classification
Chu, Wei
Champagne, Benoit
[J]. 2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13, 2006, : 5071 - 5074
[4] Efficient Noise-Robust Speech Recognition Front-End Based on the ETSI Standard
Neves, Claudio
Veiga, Arlindo
Sa, Luis
Perdigao, Fernando
[J]. ICSP: 2008 9TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, VOLS 1-5, PROCEEDINGS, 2008, : 609 - 612
[5] An Overview of Noise-Robust Automatic Speech Recognition
Li, Jinyu
Deng, Li
Gong, Yifan
Haeb-Umbach, Reinhold
[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2014, 22 (04) : 745 - 777
[6] A noise-robust front-end for distributed speech recognition in mobile communications
Addou, Djamel
Selouani, Sid-Ahmed
Kifaya, Kaoukeb
Boudraa, Malika
Boudraa, Bachir
[J]. INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2007, 10 (04) : 167 - 173
[7] A noise-robust FFT-Based auditory spectrum with application in audio classification
Chu, Wei
Champagne, Benoit
[J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2008, 16 (01): : 137 - 150
[8] Factorial Speech Processing Models for Noise-Robust Automatic Speech Recognition
Khademian, Mahdi
Homayounpour, Mohammad Mehdi
[J]. 2015 23RD IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2015, : 637 - 642
[9] A noise-robust front-end based on tree-structured filter-bank for speech recognition
Kil, RM
Kim, YI
Lee, GH
[J]. IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL VI, 2000, : 81 - 86
[10] INCORPORATING MASK MODELLING FOR NOISE-ROBUST AUTOMATIC SPEECH RECOGNITION
Koekueer, Muenevver
Jancovic, Peter
[J]. 2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 3929 - 3932

← 1 2 3 4 5 →