12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Response Probability Based Decoding Algorithm for Large Vocabulary Continuous Speech Recognition

Zhanlei Yang, Hao Chao, Wenju Liu

Chinese Academy of Sciences, China

Acoustic space is made up of phonemes, and it can be modeled using universal background model (UBM). Therefore, there are some relations between the phonemes and Gaussian mixture components of the UBM. This paper represents these relations by proposing a response probability (RP) model, which describes the location information of speech observations within the whole acoustic space. At decoding stage, proposed RP model is fused with traditional acoustic model (AM) and language model (LM). After integrating RP, the decoder is guided to weaken or enhance different path candidates respectively and directed to extend the most promising paths. Experiments conducted on Mandarin broadcasting speech show that character error rate is relatively reduced by 9.15% when RP model is used and by 11.89% when an improved RP model is used.

Full Paper

Bibliographic reference.  Yang, Zhanlei / Chao, Hao / Liu, Wenju (2011): "Response probability based decoding algorithm for large vocabulary continuous speech recognition", In INTERSPEECH-2011, 1929-1932.