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...
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...
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...
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 ...
This paper presents our work on rapid language adaptation of acoustic models based on multilingual cross-language bootstrapping and unsupervised training. We used Automatic Speech...