136
click to vote
ACL
15 years 2 months ago
2004 
This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a...
134
click to vote
NAACL
15 years 2 months ago
2004
The regular occurrence of disfluencies is a distinguishing characteristic of spontaneous speech. Detecting and removing such disfluencies can substantially improve the usefulness ...
129
Voted
CLIN
15 years 2 months ago
2004 
The disclosure of audio-visual meeting recordings is a new challenging domain studied by several large scale research projects in Europe and the US. Automatic meeting summarizatio...
125
click to vote
NAACL
15 years 2 months ago
2004
Recent work on spoken document retrieval has suggested that it is adequate to take the singlebest output of ASR, and perform text retrieval on this output. This is reasonable enou...
125
click to vote
NAACL
15 years 2 months ago
2004 
There are a lot of differences between expressions used in written language and spoken language. It is one of the reasons why speech synthesis applications are prone to produce un...
|
Computational Linguistics