Unicode-based graphemic systems for limited resource languages

Large vocabulary continuous speech recognition systems require a mapping from words, or tokens, into sub-word units to enable robust estimation of acoustic model parameters, and to model words not seen in the training data. The standard approach to achieve this is to manually generate a lexicon wher...

Full description

Saved in:
Bibliographic Details
Main Authors: Gales, M. J. F., Knill, K. M., Ragni, A.
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
Data models
Decision trees
graphemic acoustic models
Low resource speech recognition
Speech
Speech recognition
Training data
Writing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Large vocabulary continuous speech recognition systems require a mapping from words, or tokens, into sub-word units to enable robust estimation of acoustic model parameters, and to model words not seen in the training data. The standard approach to achieve this is to manually generate a lexicon where words are mapped into phones, often with attributes associated with each of these phones. Contextdependent acoustic models are then constructed using decision trees where questions are asked based on the phones and phone attributes. For low-resource languages, it may not be practical to manually generate a lexicon. An alternative approach is to use a graphemic lexicon, where the "pronunciation" for a word is defined by the letters forming that word. This paper proposes a simple approach for building graphemic systems for any language written in unicode. The attributes for graphemes are automatically derived using features from the unicode character descriptions. These attributes are then used in decision tree construction. This approach is examined on the IARPA Babel Option Period 2 languages, and a Levantine Arabic CTS task. The described approach achieves comparable, and complementary, performance to phonetic lexicon-based approaches.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2015.7178960