457 search results - page 28 / 92 » Universal background model based speech recognition |
ICASSP
2011
IEEE
14 years 1 months ago
2011
IEEE
In this work we concentrate on generating compound words with high order n-gram information for speech recognition. In most existing compound words generation methods, only bi-gra...
TASLP
2002
14 years 9 months ago
2002
Abstract--We describe some high-level approaches to estimating confidence scores for the words output by a speech recognizer. By "high-level" we mean that the proposed me...
TASLP
2002
14 years 9 months ago
2002
In this paper, we propose a robust compensation strategy to deal effectively with extraneous acoustic variations for spontaneous speech recognition. This strategy extends speaker a...
ACL
2011
14 years 1 months ago
2011
Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid...
TASLP
2002
14 years 9 months ago
2002
This paper presents a framework for maximum a posteriori (MAP) speaker adaptation of state duration distributions in hidden Markov models (HMM). Four key issues of MAP estimation, ...