Name
Abstract | ||
|---|---|---|
This paper describes a voice characteristics conversion technique for an HMM-based text-to-speech synthesis system. The system uses phoneme HMMs as the speech synthesis units, and voice characteristics conversion is achieved by changing HMM param- eters appropriately. To transform the voice characteristics of syn- thetic speech to the target speaker, we apply an MLLR (Maximum Likelihood Linear Regression) technique, one of the speaker adap- tation techniques, to the system. From the results of objective and subjective tests, it is shown that the characteristics of synthetic speech is close to target speaker's voice, and the speech generated from the adapted model set using 5 sentences has almost the same DMOS score as that from the speaker dependent model set. |
Year | Venue | Keywords |
|---|---|---|
1998 | SSW | speech synthesis |
Field | DocType | Citations |
Speech synthesis,Pattern recognition,Computer science,Speech recognition,Maximum likelihood linear regression,Speaker recognition,Speaker diarisation,Artificial intelligence,Hidden Markov model,Speaker adaptation | Conference | 41 |
PageRank | References | Authors |
6.76 | 10 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Masatsune Tamura | 1 | 107 | 15.26 |
| Takashi Masuko | 2 | 1356 | 106.53 |
| Keiichi Tokuda | 3 | 3016 | 250.00 |
| Takao Kobayashi | 4 | 1322 | 125.24 |