Noise adaptive speech recognition with acoustic models trained from noisy speech evaluated on Aurora-2 database

No Thumbnail Available
File version
Author(s)
Yao, K
Paliwal, KK
Nakamura, S
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
J.H.L. Hansen and B. Pellom
Date
2002
Size
File type(s)
Location
License
Abstract

In this paper, we apply the noise adaptive speech recognition for noisy speech recognition in non-stationary noise to the situation that acoustic models are trained from noisy speech. We justify it by that the noise adaptive speech recognition includes iterative processes between a noise parameter estimation step and a model adaptation step, which can possibly do non-linear mapping between the original training space and that for recognition. Experiments were performed on Aurora-2 task with multi-conditional training set which includes noisy utterances. Through experiments, we observed that the noise adaptive speech recognition can have better performance than the baseline system trained from multi-conditional training set without noise adaptive speech recognition.

Journal Title
Conference Title
7th International Conference on Spoken Language Processing, ICSLP 2002
Book Title
Edition
Volume
Issue
Thesis Type
Degree Program
School
DOI
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
Item Access Status
Note
Access the data
Related item(s)
Subject
Persistent link to this record
Citation