Abstract | ||
---|---|---|
This paper presents the development of acoustic and language models for robust Urdu speech recognition using the CMU Sphinx Open Source Toolkit for speech recognition. Three models have been developed incrementally, with the addition of speech data of up to two speakers per pass; one model using data from 40 female speakers only, one from 41 male speakers only, and one with both male and female speakers (81 speakers). This paper presents the current recognition results, and discusses approaches for improving these recognition rates. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1145/1943628.1943629 | FIT |
Keywords | Field | DocType |
speech recognition,cmu sphinx open source,male speaker,language model,discusses approach,current recognition result,female speaker,speech data,recognition rate,robust urdu speech recognition,large vocabulary continuous speech | Speech corpus,Computer science,Speech recognition,Speaker recognition,Urdu,Artificial intelligence,Natural language processing,VoxForge,Vocabulary,Speech technology,Language model,Sphinx | Conference |
Citations | PageRank | References |
1 | 0.40 | 5 |
Authors | ||
10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huda Sarfraz | 1 | 1 | 0.40 |
Sarmad Hussain | 2 | 96 | 12.15 |
Riffat Bokhari | 3 | 1 | 0.40 |
Agha Ali Raza | 4 | 61 | 12.10 |
Inam Ullah | 5 | 6 | 3.21 |
Zahid Sarfraz | 6 | 1 | 0.40 |
Sophia Pervez | 7 | 1 | 0.40 |
Asad Mustafa | 8 | 3 | 0.76 |
Iqra Javed | 9 | 7 | 1.55 |
Rahila Parveen | 10 | 3 | 0.76 |