Title :
An application of recurrent neural networks to low bit rate speech coding
Author_Institution :
Fac. of Eng., Tohoku Univ., Sendai, Japan
Abstract :
It is well known that the LSP coefficient which represents the speech spectrum envelope as one of the linear prediction coefficients, shows good performance for spectral interpolation along the time axis, but it is also known that the duration of interpolation is limited up to 20~30 ms. This limitation makes it difficult to reduce the bit rate in very low bit rate speech coding. To resolve this problem, recurrent neural networks (RNN) were applied to interpolate LSP coefficients, and it was possible to increase the duration of interpolation to about 100 ms without so much degradation of the synthesized speech quality
Keywords :
interpolation; linear predictive coding; recurrent neural nets; speech coding; LSP coefficient; linear prediction coefficients; low bit rate speech coding; recurrent neural networks; spectral interpolation; speech spectrum envelope; synthesized speech quality; Bit rate; Degradation; Delay effects; Ear; Interpolation; Network synthesis; Neural networks; Recurrent neural networks; Speech coding; Speech synthesis;
Conference_Titel :
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Conference_Location :
Philadelphia, PA
Print_ISBN :
0-7803-3555-4
DOI :
10.1109/ICSLP.1996.607116
