Name
Abstract | ||
|---|---|---|
New solutions to Very Low Bit Rate speech coding have been recently proposed based on speech recognition and speech synthesis technologies, [1,2,3,4,5,7,8]. In the continuation of the work described in [8], this paper presents a complete encoding scheme around 500 bits/sec. The proposed solution is based on automatic recognition of elementary acoustical units using HMM modelling. An unsupervised training phase is used to build the HMM models and the codebook of synthesis units. The decoded speech is then obtained by concatenating the corresponding synthesis units based on a HNM-like decomposition of speech. A new unit selection process is proposed integrating some prosody constraints. Through this approach, the size of the synthesis codebook is independent of the targeted bit rate. A complete description of the unit selection process and of the associated prosody modelling is given, together with the quantisation scheme of the overall set of encoded parameters. |
Year | Venue | Keywords |
|---|---|---|
2004 | EUSIPCO | hidden markov models,speech coding,speech recognition,speech synthesis,unsupervised learning,hmm modelling,vlbr speech coding,automatic recognition,elementary acoustical units,encoded parameters,speech decoding,speech synthesis technologies,synthesis units,targeted bit rate,unit selection process,unsupervised training phase,very low bit rate,very low bit rate speech coding |
Field | DocType | ISBN |
Speech processing,Speech synthesis,Speech coding,Voice activity detection,Computer science,Speech recognition,Harmonic Vector Excitation Coding,Codec2,Linear predictive coding,Acoustic model | Conference | 978-320-0001-65-7 |
Citations | PageRank | References |
3 | 0.46 | 8 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Marc Padellini | 1 | 3 | 0.80 |
| François Capman | 2 | 3 | 0.46 |
| Geneviève Baudoin | 3 | 138 | 19.08 |