Paper Info
Title
Minimization of Transition Noise and HNM Synthesis in Very Low Bit Rate Speech Coding
Abstract
The aim of our effort is to reach higher quality of resulting speech coded by very low bit rate (VLBR) segmental coder. In already existing VLBR coder [1], we want to improve the determination of acoustical units. Furthermore, better analysis-synthesis technique for the synthesis part (Harmonic-Noise Model) instead of LPCC is going to be used. The VLBR coder consists of a recognition system followed by a speech synthesizer. The recognizer identifies recognition acoustic units (RU). On the other hand, the synthesizer concatenates synthesis acoustic units (SU). However, the two kinds of acoustic unit can be identical or different and then can be modeled in different ways such Hidden Markov Model for the RU and Harmonic-Noise model for the SU. Both kinds of units are obtained automatically from a training database of raw speech that does not contain any transcription. In the original version of the coder [1], the quality of the synthetic speech was not sufficient for these two main reasons: the SU units were too short and difficult to concatenate and the synthesis was done using basic LPCC analysis-synthesis. In order to remove first drawback, three methods of resegmentation were used. Afterwards, the basic LPCC analysis-synthesis was replaced by HNM.
Year
DOI
Venue
2001
10.1007/3-540-44805-5_41
TSD
Keywords
Field
DocType
transition noise,basic lpcc analysis-synthesis,synthetic speech,acoustic unit,raw speech,harmonic-noise model,rate speech coding,segmental coder,su unit,low bit,vlbr coder,analysis-synthesis technique,speech synthesizer,hnm synthesis,speech coding,hidden markov model
Speech processing,Speech synthesis,Speech coding,Dynamic time warping,Computer science,Speech recognition,Coding (social sciences),Vector quantization,Concatenation,Hidden Markov model
Conference
ISBN
Citations 
PageRank 
3-540-42557-8
0
0.34
References 
Authors
4
4
Name
Order
Citations
PageRank
Petr Motlícek19121.81
Geneviève Baudoin213819.08
Jan Cernocký31273135.94
Gérard Chollet4725129.74