1209 search results - page 29 / 242 » Using Prosodic Features in Language Models for Meetings |
110
Voted
COLING
2008
15 years 5 months ago
2008
Psycholinguistic studies suggest a model of human language processing that 1) performs incremental interpretation of spoken utterances or written text, 2) preserves ambiguity by m...
132
Voted
ANLP
1994
15 years 4 months ago
1994
This paper proposes a model using associative processors (APs) for real-time spoken language translation. Spoken language translation requires (1) an accurate translation and (2) ...
115
Voted
ACII
2007
Springer
15 years 9 months ago
2007
Springer
Abstract. Opposing the pre-dominant turn-wise statistics of acoustic LowLevel-Descriptors followed by static classification we re-investigate dynamic modeling directly on the frame...
252
Voted
ICASSP
2011
IEEE
14 years 7 months ago
2011
IEEE
Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fea...
106
Voted
NAACL
2003
15 years 4 months ago
2003
We present a simple method for language independent and task independent text categorization learning, based on character-level n-gram language models. Our approach uses simple in...