Abstract | ||
---|---|---|
A first study on Hakka and mixed Hakka-Mandarin speech recognition (SR) is reported in this paper. The main focus of the study is on solving the problem of the lack of a large text corpus for training a reliable language model. In the Hakka SR, several methods to use the information of part of speech and Hakka-Chinese word translation to assist in language modeling are proposed. For mixed language SR, a method to train a mixed Hakka-Mandarin acoustic model is suggested. Experimental results show that the proposed language and acoustic modeling approaches are promising for Hakka and mixed Hakka-Mandarin SR. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ISCSLP.2010.5684913 | ISCSLP |
Keywords | Field | DocType |
speech processing,language modeling,speech recognition,acoustic model,language model,hakka mandarin speech recognition,language translation,hakka mandarin acoustic model,hakka,mandarin,natural language processing,hakka chinese word translation,acoustics,part of speech | Speech processing,Language translation,Computer science,Text corpus,Part of speech,Speech recognition,Natural language processing,Artificial intelligence,Language model,Mandarin Chinese,Acoustic model,Mixed language | Conference |
ISBN | Citations | PageRank |
978-1-4244-6244-5 | 2 | 0.42 |
References | Authors | |
4 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tsai-Lu Tsai | 1 | 2 | 0.42 |
Chen-Yu Chiang | 2 | 31 | 11.55 |
Hsiu-Min Yu | 3 | 11 | 2.80 |
Lieh-Shih Lo | 4 | 2 | 0.42 |
Yih-Ru Wang | 5 | 237 | 34.68 |
Sin-Horng Chen | 6 | 273 | 39.86 |