208 search results - page 18 / 42 » A Non-negative Approach to Language Informed Speech Separati... |
CSL
2006
Springer
14 years 9 months ago
2006
Springer
Enriching speech recognition output with sentence boundaries improves its human readability and enables further processing by downstream language processing modules. We have const...
CICLING
2004
Springer
15 years 1 months ago
2004
Springer
Domain shift is a challenging issue in dialogue management. This paper shows how to extract domain knowledge for dialogue model adaptation. The basic semantic concepts are derived ...
65
Voted
CIVR
2007
Springer
15 years 3 months ago
2007
Springer
Anecdotal evidence suggests that story-level information is important for the speech component of video retrieval. In this paper we perform a systematic examination of the combina...
101
click to vote
AND
2010
14 years 7 months ago
2010
High-level spoken document analysis is required in many applications seeking access to the semantic content of audio data, such as information retrieval, machine translation or au...
EMNLP
2010
14 years 7 months ago
2010
There is considerable interest in interdisciplinary combinations of automatic speech recognition (ASR), machine learning, natural language processing, text classification and info...