On combining features for single-channel robust speech recognition in reverberant environments

06/17/2019
by   José Novoa, et al.
0

This paper addresses the combination of complementary parallel speech recognition systems to reduce the error rate of speech recognition systems operating in real highly-reverberant environments. First, the testing environment consists of recordings of speech in a calibrated real room with reverberation times from 0.47 to 1.77 seconds and speaker-to-microphone distances of 0.16 to 2.56 meters. We combined systems both at the level of the DNN outputs and at the level of the final ASR outputs. Second, recognition experiments with the reverb challenge are also reported. The results presented here show that the combination of features can lead to WER improvements between 7 combination at DNN-output level is much more effective than at the system-output level. However, cascading both schemes can still lead to smaller reductions in WER.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/15/2022

Recent Progress in the CUHK Dysarthric Speech Recognition System

Despite the rapid progress of automatic speech recognition (ASR) technol...
research
09/17/2019

DOVER: A Method for Combining Diarization Outputs

Speech recognition and other natural language tasks have long benefited ...
research
11/23/2018

Improved Frequency Modulation Features for Multichannel Distant Speech Recognition

Frequency modulation features capture the fine structure of speech forma...
research
03/23/2018

Exploring the robustness of features and enhancement on speech recognition systems in highly-reverberant real environments

This paper evaluates the robustness of a DNN-HMM-based speech recognitio...
research
01/29/2018

Highly-Reverberant Real Environment database: HRRE

Speech recognition in highly-reverberant real environments remains a maj...
research
10/19/2017

Combining Multiple Views for Visual Speech Recognition

Visual speech recognition is a challenging research problem with a parti...
research
03/23/2018

An improved DNN-based spectral feature mapping that removes noise and reverberation for robust automatic speech recognition

Reverberation and additive noise have detrimental effects on the perform...

Please sign up or login with your details

Forgot password? Click here to reset