Speaker normalization for chinese vowel recognition in cochlear implants. 2005

Xin Luo, and Qian-Jie Fu
Department of Auditory Implants and Perception, House Ear Institute, 2100 West Third Street, Los Angeles, CA 90057, USA. xluo@hei.org

Because of the limited spectra-temporal resolution associated with cochlear implants, implant patients often have greater difficulty with multitalker speech recognition. The present study investigated whether multitalker speech recognition can be improved by applying speaker normalization techniques to cochlear implant speech processing. Multitalker Chinese vowel recognition was tested with normal-hearing Chinese-speaking subjects listening to a 4-channel cochlear implant simulation, with and without speaker normalization. For each subject, speaker normalization was referenced to the speaker that produced the best recognition performance under conditions without speaker normalization. To match the remaining speakers to this "optimal" output pattern, the overall frequency range of the analysis filter bank was adjusted for each speaker according to the ratio of the mean third formant frequency values between the specific speaker and the reference speaker. Results showed that speaker normalization provided a small but significant improvement in subjects' overall recognition performance. After speaker normalization, subjects' patterns of recognition performance across speakers changed, demonstrating the potential for speaker-dependent effects with the proposed normalization technique.

UI MeSH Term Description Entries
D010699 Phonation The process of producing vocal sounds by means of VOCAL CORDS vibrating in an expiratory blast of air. Phonations
D011474 Prosthesis Design The plan and delineation of prostheses in general or a specific prosthesis. Design, Prosthesis,Designs, Prosthesis,Prosthesis Designs
D002681 China A country spanning from central Asia to the Pacific Ocean. Inner Mongolia,Manchuria,People's Republic of China,Sinkiang,Mainland China
D003054 Cochlear Implants Electronic hearing devices typically used for patients with normal outer and middle ear function, but defective inner ear function. In the COCHLEA, the hair cells (HAIR CELLS, VESTIBULAR) may be absent or damaged but there are residual nerve fibers. The device electrically stimulates the COCHLEAR NERVE to create sound sensation. Auditory Prosthesis,Cochlear Prosthesis,Implants, Cochlear,Auditory Prostheses,Cochlear Implant,Cochlear Prostheses,Implant, Cochlear,Prostheses, Auditory,Prostheses, Cochlear,Prosthesis, Auditory,Prosthesis, Cochlear
D006801 Humans Members of the species Homo sapiens. Homo sapiens,Man (Taxonomy),Human,Man, Modern,Modern Man
D001185 Artificial Intelligence Theory and development of COMPUTER SYSTEMS which perform tasks that normally require human intelligence. Such tasks may include speech recognition, LEARNING; VISUAL PERCEPTION; MATHEMATICAL COMPUTING; reasoning, PROBLEM SOLVING, DECISION-MAKING, and translation of language. AI (Artificial Intelligence),Computer Reasoning,Computer Vision Systems,Knowledge Acquisition (Computer),Knowledge Representation (Computer),Machine Intelligence,Computational Intelligence,Acquisition, Knowledge (Computer),Computer Vision System,Intelligence, Artificial,Intelligence, Computational,Intelligence, Machine,Knowledge Representations (Computer),Reasoning, Computer,Representation, Knowledge (Computer),System, Computer Vision,Systems, Computer Vision,Vision System, Computer,Vision Systems, Computer
D013018 Sound Spectrography The graphic registration of the frequency and intensity of sounds, such as speech, infant crying, and animal vocalizations. Sonography, Speech,Sonography, Sound,Speech Sonography,Sonographies, Sound,Sound Sonographies,Sound Sonography,Spectrography, Sound
D013061 Speech Acoustics The acoustic aspects of speech in terms of frequency, intensity, and time. Acoustics, Speech,Acoustic, Speech,Speech Acoustic
D013067 Speech Perception The process whereby an utterance is decoded into a representation in terms of linguistic units (sequences of phonetic segments which combine to form lexical and grammatical morphemes). Speech Discrimination,Discrimination, Speech,Perception, Speech
D017076 Computer-Aided Design The use of computers for designing and/or manufacturing of anything, including drugs, surgical procedures, orthotics, and prosthetics. CAD-CAM,Computer-Aided Manufacturing,Computer-Assisted Design,Computer-Assisted Manufacturing,Computer Aided Design,Computer Aided Manufacturing,Computer Assisted Design,Computer Assisted Manufacturing,Computer-Aided Designs,Computer-Assisted Designs,Design, Computer-Aided,Design, Computer-Assisted,Designs, Computer-Aided,Designs, Computer-Assisted,Manufacturing, Computer-Aided,Manufacturing, Computer-Assisted

Related Publications

Xin Luo, and Qian-Jie Fu
December 2006, Journal of speech, language, and hearing research : JSLHR,
Xin Luo, and Qian-Jie Fu
July 1991, The Journal of the Acoustical Society of America,
Xin Luo, and Qian-Jie Fu
December 2000, The Annals of otology, rhinology & laryngology. Supplement,
Xin Luo, and Qian-Jie Fu
December 2008, The Journal of the Acoustical Society of America,
Xin Luo, and Qian-Jie Fu
November 2010, The Journal of the Acoustical Society of America,
Xin Luo, and Qian-Jie Fu
December 2006, The Journal of the Acoustical Society of America,
Xin Luo, and Qian-Jie Fu
May 2014, Acta psychologica,
Copied contents to your clipboard!