Sciweavers

INTERSPEECH
2010
12 years 12 months ago
Decision tree state clustering with word and syllable features
In large vocabulary continuous speech recognition, decision trees are widely used to cluster triphone states. In addition to commonly used phonetically based questions, others hav...
Hank Liao, Christopher Alberti, Michiel Bacchiani,...
INTERSPEECH
2010
12 years 12 months ago
Improved neural network based language modelling and adaptation
Neural network language models (NNLM) have become an increasingly popular choice for large vocabulary continuous speech recognition (LVCSR) tasks, due to their inherent generalisa...
Junho Park, Xunying Liu, Mark J. F. Gales, Philip ...
INTERSPEECH
2010
12 years 12 months ago
A spoken term detection framework for recovering out-of-vocabulary words using the web
Vocabulary restrictions in large vocabulary continuous speech recognition (LVCSR) systems mean that out-of-vocabulary (OOV) words are lost in the output. However, OOV words tend t...
Carolina Parada, Abhinav Sethy, Mark Dredze, Frede...
TASLP
2002
110views more  TASLP 2002»
13 years 4 months ago
Automatic generation of subword units for speech recognition systems
Large vocabulary continuous speech recognition (LVCSR) systems traditionally represent words in terms of smaller subword units. Both during training and during recognition, they re...
Rita Singh, Bhiksha Raj, Richard M. Stern
NAACL
1994
13 years 6 months ago
Language Identification via Large Vocabulary Speaker Independent Continuous Speech Recognition
The goal of this study is to evaluate the potential for using large vocabulary continuous speech recognition as an engine for automatically classifying utterances according to the...
Steve Lowe, Anne Demedts, Larry Gillick, Mark Mand...
LREC
2008
111views Education» more  LREC 2008»
13 years 6 months ago
Developing Corpus of Japanese Classroom Lecture Speech Contents
This paper explains our developing Corpus of Japanese classroom Lecture speech Contents (henceforth, denoted as CJLC). Increasing e-Learning contents demand a sophisticated intera...
Masatoshi Tsuchiya, Satoru Kogure, Hiromitsu Nishi...