Abstract | ||
---|---|---|
This paper applies the latent words language model (LWLM) to automatic speech recognition (ASR). LWLMs are trained taking into account related words, i.e., grouping of similar words in terms of meaning and syntactic role. This means, for example, if a technical word and a general word play a similar syntactic role, they are given a similar probability. This is expected that the LWLM performs robustly over multiple domains. Furthermore, we can expect that the interpolation of the LWLM and a standard n-gram LM will be effective since each of the LMs have different learning criterion. In addition, this paper also describes an approximation method of the LWLM for ASR, in which words are randomly sampled on the LWLM and then a standard word n-gram language model is trained. This enables us one-pass decoding. Our experimental results show that the LWLM performs comparable to the hierarchical Pitman-Yor language model (HPYLM) in a target domain task, and more robustly performs in out-domain tasks. Moreover, an interpolation model with the HPYLM provides a lower word error rate in all the tasks. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICASSP.2013.6639313 | 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Keywords | Field | DocType |
Latent words language model, Hierarchical Pitman-Yor language model, Sampling-based implementation | Cache language model,Computer science,Interpolation,Natural language processing,n-gram,Artificial intelligence,Syntax,Language model,Factored language model,Pattern recognition,Word error rate,Computational linguistics,Speech recognition | Conference |
ISSN | Citations | PageRank |
1520-6149 | 5 | 0.44 |
References | Authors | |
12 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ryo Masumura | 1 | 25 | 28.24 |
Hirokazu Masataki | 2 | 18 | 9.21 |
Takanobu Oba | 3 | 53 | 12.09 |
Osamu Yoshioka | 4 | 29 | 5.66 |
Satoshi Takahashi | 5 | 5 | 1.46 |