Sciweavers

Share
85 search results - page 1 / 17
» Unsupervised acoustic and language model training with small...
Sort
View
ICASSP
2009
IEEE
10 years 6 months ago
Unsupervised acoustic and language model training with small amounts of labelled data
We measure the effects of a weak language model, estimated from as little as 100k words of text, on unsupervised acoustic model training and then explore the best method of using ...
Scott Novotney, Richard M. Schwartz, Jeff Ma
CSL
2002
Springer
9 years 11 months ago
Lightly supervised and unsupervised acoustic model training
The last decade has witnessed substantial progress in speech recognition technology, with todays state-of-the-art systems being able to transcribe unrestricted broadcast news audi...
Lori Lamel, Jean-Luc Gauvain, Gilles Adda
INTERSPEECH
2010
9 years 6 months ago
Unsupervised discovery and training of maximally dissimilar cluster models
One of the difficult problems of acoustic modeling for Automatic Speech Recognition (ASR) is how to adequately model the wide variety of acoustic conditions which may be present i...
Françoise Beaufays, Vincent Vanhoucke, Bria...
ICASSP
2011
IEEE
9 years 3 months ago
Lattice-based unsupervised acoustic model training
Unsupervised acoustic model training has been successfully used to improve the performance of automatic speech recognition systems when only a small amount of manually transcribed...
Thiago Fraga-Silva, Jean-Luc Gauvain, Lori Lamel
ICASSP
2011
IEEE
9 years 3 months ago
Acoustic data sharing for Afghan and Persian languages
In this work, we compare several known approaches for multilingual acoustic modeling for three languages, Dari, Farsi and Pashto, which are of recent geo-political interest. We de...
Arindam Mandal, Dimitra Vergyri, Murat Akbacak, Co...
books