Name
Abstract | ||
|---|---|---|
This paper presents a variable-length unit selection scheme based on syntactic cost to select text-to-speech (TTS) synthesis units. The syntactic structure of a sentence is derived from a probabilistic context-free grammar (PCFG), and represented as a syntactic vector. The syntactic difference between target and candidate units (words or phrases) is estimated by the cosine measure with the inside probability of PCFG acting as a weight. Latent semantic analysis (LSA) is applied to reduce the dimensionality of the syntactic vectors. The dynamic programming algorithm is adopted to obtain a concatenated unit sequence with minimum cost. A syntactic property-rich speech database is designed and collected as the unit inventory. Several experiments with statistical testing are conducted to assess the quality of the synthetic speech as perceived by human subjects. The proposed method outperforms the synthesizer without considering syntactic property. The structural syntax estimates the substitution cost better than the acoustic features alone |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/TASL.2006.889752 | IEEE Transactions on Audio, Speech & Language Processing |
Keywords | Field | DocType |
syntactic property-rich speech database,probabilistic context-free grammar,minimum cost,syntactic vector,statistical testing,variable-length unit selection,syntactic difference,structural syntactic cost,tts,syntactic cost,probabilistic context-free grammar (pcfg),concatenated unit sequence,candidate unit,latent semantic analysis,speech synthesis,syntactic structure,substitution cost,dynamic programming algorithm,text-to-speech synthesis,dynamic programming,latent semantic analysis (lsa),structural syntax,syntactic property,computer science,concatenated codes,statistical test,text to speech,statistical analysis | Speech processing,Speech synthesis,Context-free grammar,Computer science,Speech recognition,Natural language processing,Artificial intelligence,Probabilistic logic,Latent semantic analysis,Syntax,Sentence,Statistical hypothesis testing | Journal |
Volume | Issue | ISSN |
15 | 4 | 1558-7916 |
Citations | PageRank | References |
8 | 0.59 | 19 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chung-Hsien Wu | 1 | 1099 | 116.79 |
| C. -C. Hsia | 2 | 8 | 0.59 |
| Jiun-Fu Chen | 3 | 10 | 1.32 |
| Jhing-fa Wang | 4 | 982 | 114.31 |