16th Annual Conference of the International Speech Communication Association

Dresden, Germany
September 6-10, 2015

Recognize Foreign Low-Frequency Words with Similar Pairs

Xi Ma, Xiaoxi Wang, Dong Wang, Zhiyong Zhang

Tsinghua University, China

Low-frequency words place a major challenge for automatic speech recognition (ASR). The probabilities of these words, which are often important name entities, are generally under-estimated by the language model (LM) due to their limited occurrences in the training data. Recently, we proposed a word-pair approach to deal with the problem, which borrows information of frequent words to enhance the probabilities of low-frequency words. This paper presents an extension to the word-pair method by involving multiple `predicting words' to produce better estimation for low-frequency words. We also employ this approach to deal with out-of-language words in the task of multi-lingual speech recognition.

Full Paper

Bibliographic reference.  Ma, Xi / Wang, Xiaoxi / Wang, Dong / Zhang, Zhiyong (2015): "Recognize foreign low-frequency words with similar pairs", In INTERSPEECH-2015, 458-462.