Conference proceeding
DEEP CONVOLUTIONAL ACOUSTIC WORD EMBEDDINGS USING WORD-PAIR SIDE INFORMATION
2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, Vol.2016-, pp.4950-4954
International Conference on Acoustics Speech and Signal Processing ICASSP
03/01/2016
DOI: 10.1109/icassp.2016.7472619
Abstract
Recent studies have been revisiting whole words as the basic modelling unit in speech recognition and query applications, instead of phonetic units. Such whole-word segmental systems rely on a function that maps a variable-length speech segment to a vector in a fixed-dimensional space; the resulting acoustic word embeddings need to allow for accurate discrimination between different word types, directly in the embedding space. We compare several old and new approaches in a word discrimination task. Our best approach uses side information in the form of known word pairs to train a Siamese convolutional neural network (CNN): a pair of tied networks that take two speech segments as input and produce their embeddings, trained with a hinge loss that separates same-word pairs and different-word pairs by some margin. A word classifier CNN performs similarly, but requires much stronger supervision. Both types of CNNs yield large improvements over the best previously published results on the word discrimination task.
Details
- Title: Subtitle
- DEEP CONVOLUTIONAL ACOUSTIC WORD EMBEDDINGS USING WORD-PAIR SIDE INFORMATION
- Creators
- Herman Kamper - University of EdinburghWeiran Wang - Toyota Technol Inst Chicago, Chicago, IL USAKaren Livescu - Toyota Technol Inst Chicago, Chicago, IL USA
- Resource Type
- Conference proceeding
- Publication Details
- 2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, Vol.2016-, pp.4950-4954
- Publisher
- IEEE
- Series
- International Conference on Acoustics Speech and Signal Processing ICASSP
- DOI
- 10.1109/icassp.2016.7472619
- ISSN
- 1520-6149
- eISSN
- 2379-190X
- Number of pages
- 5
- Language
- English
- Date published
- 03/01/2016
- Academic Unit
- Computer Science
- Record Identifier
- 9984696560802771
Metrics
1 Record Views