Title :
A vocoder based on speech recognition and synthesis
Author :
Yi, Kechu ; Cheng, Jun ; Wang, Anliang ; Zhang, Pu ; Liu, Feng ; Li, Weiying ; Yang, Bin ; Du, Shuanyi ; Jun Gong
Author_Institution :
Nat Key Lab. of Integrated Service Networks, Xidian Univ., Xi´´an, China
Abstract :
This paper introduces a speech recognition and synthesis based (SRSB) vocoder made by the authors, which has been judged by experts recently. The SRSB vocoder can encode Chinese speech of unlimited vocabulary at a bit rate of lower than 200 bps and reproduce speech with intelligibility of 95.2%. The vocoder consists of a real-time syllable recognizer to encode syllables based on composite hidden Markov modeling and a speech synthesizer to reproduce speech with syllable concatenation based on pitch-synchronous overlap-adding algorithm (PSOLA). It is capable of good prosodic modifications, since it can make use of prosodic parameters extracted from the input voice. Either terminal of it is implemented with an IBM-PC microcomputer equipped with a TMS320C30 DSP subsystem
Keywords :
digital signal processing chips; hidden Markov models; speech coding; speech intelligibility; speech recognition; speech synthesis; vocoders; 200 bit/s; Chinese speech; IBM-PC microcomputer; SRSB vocoder; TMS320C30 DSP subsystem; composite hidden Markov model; pitch-synchronous overlap-adding algorithm; prosodic modifications; real-time syllable recognizer; speech intelligibility; speech recognition; speech synthesis; syllable concatenation; unlimited vocabulary; vocoder; Bit rate; Hidden Markov models; Network synthesis; Speech coding; Speech processing; Speech recognition; Speech synthesis; Synthesizers; Vocabulary; Vocoders;
Conference_Titel :
Global Telecommunications Conference, 1995. GLOBECOM '95., IEEE
Print_ISBN :
0-7803-2509-5
DOI :
10.1109/GLOCOM.1995.500296
