162
click to vote
ACL
15 years 4 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...
158
click to vote
NAACL
15 years 4 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 ...
150
click to vote
CLIN
15 years 4 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...
144
click to vote
NAACL
15 years 4 months ago
2004
State-of-the-art story link detection systems, that is, systems that determine whether two stories are about the same event or linked, are usually based on the cosine-similarity m...
143
click to vote
NAACL
15 years 4 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