Sciweavers

963 search results - page 20 / 193
» Rethinking Algorithm Design and Development in Speech Proces...
Sort
View
ICASSP
2008
IEEE
14 years 2 months ago
Computationally efficient equalization of room impulse responses robust to system estimation errors
Equalization techniques for room impulse responses (RIRs) are important in acoustic signal processing applications such as speech dereverberation. In practice, only approximate es...
Wancheng Zhang, Nikolay D. Gaubitch, Patrick A. Na...
MICAI
2007
Springer
14 years 1 months ago
An EM Algorithm to Learn Sequences in the Wavelet Domain
The wavelet transform has been used for feature extraction in many applications of pattern recognition. However, in general the learning algorithms are not designed taking into acc...
Diego H. Milone, Leandro E. Di Persia
ICRA
2009
IEEE
137views Robotics» more  ICRA 2009»
14 years 2 months ago
Continuous vocal imitation with self-organized vowel spaces in Recurrent Neural Network
Abstract— A continuous vocal imitation system was developed using a computational model that explains the process of phoneme acquisition by infants. Human infants perceive speech...
Hisashi Kanda, Tetsuya Ogata, Toru Takahashi, Kazu...
ICASSP
2008
IEEE
14 years 2 months ago
ITU-T G.EV-VBR baseline codec
We present the G.EV-VBR winning candidate codec recently selected by Question 9 of Study Group 16 (Q9/16) of ITU-T as a baseline for the development of a scalable solution for wid...
Milan Jelinek, Tommy Vaillancourt, A. Erdem Ertan,...
ICMCS
2009
IEEE
102views Multimedia» more  ICMCS 2009»
13 years 5 months ago
Scalable HMM based inference engine in large vocabulary continuous speech recognition
Parallel scalability allows an application to efficiently utilize an increasing number of processing elements. In this paper we explore a design space for parallel scalability for...
Jike Chong, Kisun You, Youngmin Yi, Ekaterina Goni...