Paper Info
Title
Improved Subword Modeling For Wfst-Based Speech Recognition
Abstract
Because in agglutinative languages the number of observed word forms is very high, subword units are often utilized in speech recognition. However, the proper use of subword units requires careful consideration of details such as silence modeling. position-dependent phones. and combination of the units. In this paper, we implement subword modeling in the Kaldi toolkit by creating modified lexicon by finite-state transducers to represent the subword units correctly. We experiment with multiple types of word boundary markers and achieve the best results by adding a marker to the left or right side of a subword unit whenever it is not preceded or followed by a word boundary, respectively. We also compare three different toolkits that provide data-driven subword segmentations. In our experiments on a variety of Finnish and Estonian datasets, the best subword models do outperform word-based models and naive subword implementations. The largest relative reduction in WER is a 23% over word-based models for a Finnish read speech dataset. The results are also better than any previously published ones for the same datasets, and the improvement on all datasets is more than 5%.
Year
DOI
Venue
2017
10.21437/Interspeech.2017-103
18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION
Keywords
Field
DocType
speech recognition, Kaldi, subword modeling, Finnish, Estonian
Estonian,Computer science,Speech recognition,Natural language processing,Artificial intelligence
Conference
ISSN
Citations 
PageRank 
2308-457X
3
0.41
References 
Authors
0
3
Name
Order
Citations
PageRank
Peter Smit1185.08
Sami Virpioja229925.51
Mikko Kurimo390893.37