Abstract | ||
---|---|---|
In this paper, a structural maximum a posteriori (SMAP) speaker adaptation approach to adjusting the speaking rate (SR)-dependent hierarchical prosodic model (SR-HPM) of an existing SR-controlled Mandarin text-to-speech system to a new speaker's data for producing a new voice is discussed. Two main issues are addressed. One is the small SR coverage of the adaptation data and is solved by using the... |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/TASLP.2016.2598307 | IEEE/ACM Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
Hidden Markov models,Adaptation models,Speech,Pragmatics,Data models,Speech synthesis,Linear regression | Speech corpus,Decision tree,Data modeling,Speech synthesis,Computer science,Speech recognition,Natural language processing,Artificial intelligence,Speaker diarisation,Maximum a posteriori estimation,Hidden Markov model,Mandarin Chinese | Journal |
Volume | Issue | ISSN |
24 | 11 | 2329-9290 |
Citations | PageRank | References |
1 | 0.36 | 31 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
I.-Bin Liao | 1 | 4 | 1.12 |
Chen-Yu Chiang | 2 | 31 | 11.55 |
Yih-Ru Wang | 3 | 237 | 34.68 |
Sin-Horng Chen | 4 | 273 | 39.86 |