2006 · 49 citations · 8 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingDeep LearningLanguage AdaptationLanguage ModelingLanguage ModelsSpeech RecognitionLanguage Model Pretraining
Lack of data is a problem in training language models for conversational speech recognition, particularly for languages other than English. Experiments in English have successfully used Web-based text collection, targeted for a conversational style, to augment small sets of transcribed speech; we look at extending these techniques to Mandarin. In addition, we investigate different techniques for topic adaptation. Experiments in recognizing Mandarin telephone conversations show that the use of filtered Web data leads to a 28% reduction in perplexity and 7% reduction in character error rate, with most of the gain due to the general filtered Web data.
8
Improving trigram language modeling with the World Wide Web
Xiaojin Zhu, Roni Rosenfeld · 2002 · 126 citations · Full text
Just-in-time language modelling
Adam Berger, Robert J. Miller · 2002 · 52 citations