Denoised Bottleneck Features From Deep Autoencoders for Telephone Conversation Analysis

Automatic transcription of spoken documents is affected by automatic transcription errors that are especially frequent when speech is acquired in severe noisy conditions. Automatic speech recognition errors induce errors in the linguistic features used for a variety of natural language processing ta...

Full description

Saved in:
Bibliographic Details
Published in:IEEE/ACM transactions on audio, speech, and language processing Vol. 25; no. 9; pp. 1809 - 1820
Main Authors: Janod, Killian, Morchid, Mohamed, Dufour, Richard, Linares, Georges, De Mori, Renato
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.09.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Institute of Electrical and Electronics Engineers
Subjects:
Acoustic noise
Artificial Intelligence
Automatic speech recognition
Automatic speech recognition (ASR)
Computer Science
Conversation
Conversation analysis
Denoising
denoisng autoencoders (DAEs)
Document and Text Processing
Feature extraction
Feature recognition
Manuals
multilayer neural networks
Natural language processing
Noise measurement
Noise reduction
Recovery
Representations
Robustness
Semantics
Speech
speech analytics
Speech processing
Speech recognition
stacked autoencoders (SAEs)
Transcription
Voice recognition
ISSN:2329-9290, 2329-9304
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Automatic transcription of spoken documents is affected by automatic transcription errors that are especially frequent when speech is acquired in severe noisy conditions. Automatic speech recognition errors induce errors in the linguistic features used for a variety of natural language processing tasks. Recently, denoisng autoencoders (DAE) and stacked autoencoders (SAE) have been proposed with interesting results for acoustic feature denoising tasks. This paper deals with the recovery of corrupted linguistic features in spoken documents. Solutions based on DAEs and SAEs are considered and evaluated in a spoken conversation analysis task. In order to improve conversation theme classification accuracy, the possibility of combining abstractions obtained from manual and automatic transcription features is considered. As a result, two original representations of highly imperfect spoken documents are introduced. They are based on bottleneck features of a supervised autoencoder that takes advantage of both noisy and clean transcriptions to improve the robustness of error prone representations. Experimental results on a spoken conversation theme identification task show substantial accuracy improvements obtained with the proposed recovery of corrupted features.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2329-9290
2329-9304
DOI:10.1109/TASLP.2017.2718843