Title: Accounting for uncertainity in observations: A new paradigm for Robust Automatic Speech Recognition
Abstract:We introduce a new paradigm for Robust Automatic Speech Recognition that directly incorporates information about the uncertainty introduced by environmental noise. In contrast to the feature cleaning ...We introduce a new paradigm for Robust Automatic Speech Recognition that directly incorporates information about the uncertainty introduced by environmental noise. In contrast to the feature cleaning and model adaptation paradigms, where the noise compensation mechanism is separate from the recognizer, the new paradigm unifies the noise compensation mechanism and the recognizer. The Algonquin framework serves to demonstrate the importance of retaining soft information, i.e. information about the degree of uncertainty in the observations. The Algonquin framework employs Gaussian mixture models to model both noise and speech. Uncertainty introduced by the noise process is captured by the variance of the noise model. The Algonquin framework also allows us to isolate the effect of retaining or discarding soft information. Our initial results indicate that substantial improvements in recognition rates can be achieved through the use of soft information.Read More
Publication Year: 2002
Publication Date: 2002-05-01
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
Cited By Count: 41
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot