Conference paper

MOTLÍČEK Petr, BAUDOIN Genevieve, ČERNOCKÝ Jan and CHOLLET Gerard. Minimization of transition noise and HNM synthesis in very low bit rate speech coding. In: 4th International Conference, TSD 2001 Železná Ruda, Czech Republic, September 2001 Proceedings. Berlin: Springer Verlag, 2001, pp. 305-312. ISBN 3-540-42557-8.
Publication language:english
Original title:Minimization of transition noise and HNM synthesis in very low bit rate speech coding
Title (cs):Minimalizace přechodového šumu a HNM syntéza v kódování řeči na nízkých bitových rychlostech
Pages:305-312
Proceedings:4th International Conference, TSD 2001 Železná Ruda, Czech Republic, September 2001 Proceedings
Conference:International Conference on Text Speech and Dialogue, TSD 2001
Place:Berlin, DE
Year:2001
ISBN:3-540-42557-8
Publisher:Springer Verlag
URL:http://www.fit.vutbr.cz/~motlicek/publi/2001/tsd01.ps [PS]
Keywords
speech coding, speech recognition, speech synthesis, feature extraction
Annotation
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, 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, 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 re-segmentation were used. Afterwards, the basic LPCC analysis-synthesis was replaced by HNM.
BibTeX:
@INPROCEEDINGS{
   author = {Petr Motl{\'{i}}{\v{c}}ek and Genevieve Baudoin and Jan
	{\v{C}}ernock{\'{y}} and Gerard Chollet},
   title = {Minimization of transition noise and HNM synthesis in very
	low bit rate speech coding},
   pages = {305--312},
   booktitle = {4th International Conference, TSD 2001 {\v{Z}}elezn{\'{a}}
	Ruda, Czech Republic, September 2001 Proceedings},
   year = {2001},
   location = {Berlin, DE},
   publisher = {Springer Verlag},
   ISBN = {3-540-42557-8},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=7145}
}

Your IPv4 address: 54.82.79.109
Switch to IPv6 connection

DNSSEC [dnssec]