2406 search results - page 46 / 482 » Visualizations: speech, language |
100
click to vote
ICASSP
2010
IEEE
15 years 2 days ago
2010
IEEE
We present a novel discriminative training algorithm for n-gram language models for use in large vocabulary continuous speech recognition. The algorithm uses large margin estimati...
103
click to vote
LREC
2008
15 years 1 months ago
2008
Language models used in current automatic speech recognition systems are trained on general-purpose corpora and are therefore not relevant to transcribe spoken documents dealing w...
INTERSPEECH
2010
14 years 6 months ago
2010
This paper presents a new approach to language model construction, learning a language model not from text, but directly from continuous speech. A phoneme lattice is created using...
112
click to vote
TASLP
2010
14 years 6 months ago
2010
Traditional n-gram language models are widely used in state-of-the-art large vocabulary speech recognition systems. This simple model suffers from some limitations, such as overfi...
LREC
2010
15 years 1 months ago
2010
A speech database, named KALAKA, was created to support the Albayzin 2008 Evaluation of Language Recognition Systems, organized by the Spanish Network on Speech Technologies from ...