Speaker normalization for Chinese vowel recognition in cochlear implants

• Published in: IEEE transactions on biomedical engineering Vol. 52; no. 7; pp. 1358 - 1361
• Main Authors: Luo, X., Fu, Q.-J.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2005; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial Intelligence; Auditory implants; China; Cochlear Implants; Computer-Aided Design; Equipment Failure Analysis; Filter bank; Frequency; Humans; Pattern analysis; Pattern matching; Pattern recognition; Phonation; Prosthesis Design; Sound Spectrography - methods; speaker normalization; Speech Acoustics; Speech Perception; Speech processing; Speech recognition; Speech Recognition Software; Testing; Transplants & implants; vowel recognition; China
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2005.847530

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.