A novel algorithm for unsupervised prosodic language model adaptation

Symbolic representations of prosodic events have been shown to be useful for spoken language applications such as speech recognition. However, a major drawback with categorical prosody models is their lack of scalability due to the difficulty in annotating large corpora with prosodic tags for traini...

Full description

Saved in:
Bibliographic Details
Published in:2008 IEEE International Conference on Acoustics, Speech and Signal Processing Speech and Signal Processing, 2008-01 (4518576), p.4181-4184
Main Authors: Ananthakrishnan, Sankaranarayanan, Narayanan, Shrikanth
Format: Article
Language:English
Subjects:
Adaptation model
Automatic speech recognition
Labeling
Laboratories
lattice posterior
Lattices
Natural languages
pitch accent
prosodic language model
prosody
Speech analysis
Speech recognition
Stress
Testing
unsupervised adaptation
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Symbolic representations of prosodic events have been shown to be useful for spoken language applications such as speech recognition. However, a major drawback with categorical prosody models is their lack of scalability due to the difficulty in annotating large corpora with prosodic tags for training. In this paper, we present a novel, unsupervised adaptation technique for bootstrapping categorical prosodic language models (PLMs) from a small, annotated training set. Our experiments indicate that the adaptation algorithm significantly improves the quality and coverage of the PLM. On a test set derived from the Boston University Radio News corpus, the adapted PLM gave a relative improvement of 13.8% over the seed PLM on the binary pitch accent detection task, while reducing the OOV rate by 16.5% absolute.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2008.4518576