Title :
Balancing acoustic and linguistic probabilities
Author :
Ogawa, Atsunori ; Takeda, Kazuya ; Itakura, Fumitala
Author_Institution :
Dept. of Inf. Electron., Nagoya Univ., Japan
Abstract :
The length of the word sequence is not taken into account under language modeling of n-gram local probability modeling. Due to this property the optimal values of the language weight and word insertion penalty for balancing acoustic and linguistic probabilities is affected by the length of word sequence. To deal with this problem, a new language model is developed based on the Bernoulli trial model taking the length of the word sequence into account. Not only better recognition accuracy but also more robust balancing with acoustic probability compared with the normal n-gram model of the proposed method is confirmed through recognition experiments
Keywords :
linguistics; optimisation; probability; speech recognition; Bernoulli trial model; Ngram language model; acoustic probability; language weight; linguistic probability; optimisation; speech recognition; word insertion penalty; word sequence; Robustness; Speech recognition; Stochastic processes;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.674397