Conference proceeding
ACOUSTIC FEATURE LEARNING USING CROSS-DOMAIN ARTICULATORY MEASUREMENTS
2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), Vol.2018-, pp.4849-4853
01/01/2018
DOI: 10.1109/ICASSP.2018.8461818
Abstract
Previous work has shown that it is possible to improve speech recognition by learning acoustic features from paired acoustic-articulatory data, for example by using canonical correlation analysis (CCA) or its deep extensions. One limitation of this prior work is that the learned feature models are difficult to port to new datasets or domains, and articulatory data is not available for most speech corpora. In this work we study the problem of acoustic feature learning in the setting where we have access to an external, domain-mismatched dataset of paired speech and articulatory measurements, either with or without labels. We develop methods for acoustic feature learning in these settings, based on deep variational CCA and extensions that use both source and target domain data and labels. Using this approach, we improve phonetic recognition accuracies on both TIMIT and Wall Street Journal and analyze a number of design choices.
Details
- Title: Subtitle
- ACOUSTIC FEATURE LEARNING USING CROSS-DOMAIN ARTICULATORY MEASUREMENTS
- Creators
- Qingming Tang - Toyota Technological Institute at ChicagoWeiran Wang - AmazonKaren Livescu - Toyota Technological Institute at Chicago
- Resource Type
- Conference proceeding
- Publication Details
- 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), Vol.2018-, pp.4849-4853
- Publisher
- IEEE
- DOI
- 10.1109/ICASSP.2018.8461818
- ISSN
- 1520-6149
- eISSN
- 2379-190X
- Number of pages
- 5
- Language
- English
- Date published
- 01/01/2018
- Academic Unit
- Computer Science
- Record Identifier
- 9984696560602771
Metrics
7 Record Views