Name
Abstract | ||
|---|---|---|
This paper presents a new Very Low Bit Rate segmental speech coding approach applying speech recognition in the coder and corpus based speech synthesis in the decoder. The system uses a large corpus of speech signal that is searched to find a speech segment similar to the segment to be coded. The elementary acoustical units for recognition and synthesis are determined automatically by an unsupervised training method. This approach is an alternative to using phoneme-derived linguistic units.Very good results are obtained at an average bit rate of 400 bits/second for a corpus of about 1 hour of speech. We present an efficient method for finding the best synthesis unit taking into account the good concatenation of successive segments. The proposed organization of the speech segments in the corpus allows a very efficient search of the best unit. |
Year | DOI | Venue |
|---|---|---|
2003 | 10.1109/ICASSP.2003.1198900 | ICASSP |
Keywords | Field | DocType |
search problems,speech coding,speech recognition,speech synthesis,vocoders,400 bit/s,corpus based speech synthesis,elementary acoustical units,searching,segmental speech coding,speech coder,speech recognition,speech segment,successive segment concatenation,synthesis unit,unsupervised training method,very low bit rate speech coding | Speech synthesis,Speech coding,Pattern recognition,Voice activity detection,Computer science,Speech recognition,Artificial intelligence,Concatenation,Codec2,Harmonic Vector Excitation Coding,Hidden Markov model,Linear predictive coding | Conference |
Volume | Citations | PageRank |
1 | 7 | 0.51 |
References | Authors | |
8 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Geneviève Baudoin | 1 | 138 | 19.08 |
| Fadi El Chami | 2 | 15 | 1.18 |