An objective identification of spectral distinctiveness on acoustic cue to subjects with hearing loss

Y. J. Chen, M. D. Lee, Jiunn-Liang Wu, H. M. Yang, Y. H. Lin

Research output: Contribution to conferencePaper

Abstract

Hearing loss would seriously degrade a subject's speech perception, thereby affecting the development of articulation ability. Assistive listening devices such as hearing aids or cochlear implants could help subjects with hearing loss develop their speech perception. To facilitate this process, speech-language patholo-gists (SLPs) provide speech-perception training that can increase the subject's ability to distinguish one phoneme from another. In clinical practice, they manually enhance the acoustic cues and use this information therein to teach a subject the differences between two phonemes. However, it is a time-consuming and expensive process. In this study, an objective identification of spectral distinctiveness is proposed to find the acoustic cues between two phonemes. SLPs then could use it to facilitate the speech-perception training process. Mel-frequency cep-strum coefficients (MFCCs) are selected to accurately represent the characteristics of acoustic signal. To deal the mismatch between two phonemes in time domain, the Viterbi algorithm is integrated to find a best matching condition. In order to estimate the spectral similarity, the speech signal is decomposed into different frequency bands. For each bands, MFCCs are also applied to represent the characteristic of filtered speech signals. According to the best matching condition, the spectral distinctiveness of different bands between two phonemes could be easily estimated by using Euclidean metrics. Finally, the morphological gradient is adopted to find the sections of spectral distinctiveness. To evaluate the correction of proposed approach, the speech signal of identified spectral distinctiveness was manually manipulated, and then the manipulated speeches are evaluated by a close-set detection evaluation methodology. The experimental results demonstrated that our approach is able to identify a suitable spectral distinctiveness.

Original languageEnglish
Pages195-198
Number of pages4
Publication statusPublished - 2014 Jan 1
Event2nd International Conference on Innovation, Communication and Engineering, ICICE 2013 - Qingdao, China
Duration: 2013 Oct 262013 Nov 1

Other

Other2nd International Conference on Innovation, Communication and Engineering, ICICE 2013
CountryChina
CityQingdao
Period13-10-2613-11-01

Fingerprint

Audition
Acoustics
Frequency bands
Distinctiveness
Cochlear implants
Hearing aids
Viterbi algorithm
Information use
Coefficients
Language

All Science Journal Classification (ASJC) codes

  • Management of Technology and Innovation

Cite this

Chen, Y. J., Lee, M. D., Wu, J-L., Yang, H. M., & Lin, Y. H. (2014). An objective identification of spectral distinctiveness on acoustic cue to subjects with hearing loss. 195-198. Paper presented at 2nd International Conference on Innovation, Communication and Engineering, ICICE 2013, Qingdao, China.
Chen, Y. J. ; Lee, M. D. ; Wu, Jiunn-Liang ; Yang, H. M. ; Lin, Y. H. / An objective identification of spectral distinctiveness on acoustic cue to subjects with hearing loss. Paper presented at 2nd International Conference on Innovation, Communication and Engineering, ICICE 2013, Qingdao, China.4 p.
@conference{a1d518c174534d17bb0efa0901384dd3,
title = "An objective identification of spectral distinctiveness on acoustic cue to subjects with hearing loss",
abstract = "Hearing loss would seriously degrade a subject's speech perception, thereby affecting the development of articulation ability. Assistive listening devices such as hearing aids or cochlear implants could help subjects with hearing loss develop their speech perception. To facilitate this process, speech-language patholo-gists (SLPs) provide speech-perception training that can increase the subject's ability to distinguish one phoneme from another. In clinical practice, they manually enhance the acoustic cues and use this information therein to teach a subject the differences between two phonemes. However, it is a time-consuming and expensive process. In this study, an objective identification of spectral distinctiveness is proposed to find the acoustic cues between two phonemes. SLPs then could use it to facilitate the speech-perception training process. Mel-frequency cep-strum coefficients (MFCCs) are selected to accurately represent the characteristics of acoustic signal. To deal the mismatch between two phonemes in time domain, the Viterbi algorithm is integrated to find a best matching condition. In order to estimate the spectral similarity, the speech signal is decomposed into different frequency bands. For each bands, MFCCs are also applied to represent the characteristic of filtered speech signals. According to the best matching condition, the spectral distinctiveness of different bands between two phonemes could be easily estimated by using Euclidean metrics. Finally, the morphological gradient is adopted to find the sections of spectral distinctiveness. To evaluate the correction of proposed approach, the speech signal of identified spectral distinctiveness was manually manipulated, and then the manipulated speeches are evaluated by a close-set detection evaluation methodology. The experimental results demonstrated that our approach is able to identify a suitable spectral distinctiveness.",
author = "Chen, {Y. J.} and Lee, {M. D.} and Jiunn-Liang Wu and Yang, {H. M.} and Lin, {Y. H.}",
year = "2014",
month = "1",
day = "1",
language = "English",
pages = "195--198",
note = "2nd International Conference on Innovation, Communication and Engineering, ICICE 2013 ; Conference date: 26-10-2013 Through 01-11-2013",

}

Chen, YJ, Lee, MD, Wu, J-L, Yang, HM & Lin, YH 2014, 'An objective identification of spectral distinctiveness on acoustic cue to subjects with hearing loss' Paper presented at 2nd International Conference on Innovation, Communication and Engineering, ICICE 2013, Qingdao, China, 13-10-26 - 13-11-01, pp. 195-198.

An objective identification of spectral distinctiveness on acoustic cue to subjects with hearing loss. / Chen, Y. J.; Lee, M. D.; Wu, Jiunn-Liang; Yang, H. M.; Lin, Y. H.

2014. 195-198 Paper presented at 2nd International Conference on Innovation, Communication and Engineering, ICICE 2013, Qingdao, China.

Research output: Contribution to conferencePaper

TY - CONF

T1 - An objective identification of spectral distinctiveness on acoustic cue to subjects with hearing loss

AU - Chen, Y. J.

AU - Lee, M. D.

AU - Wu, Jiunn-Liang

AU - Yang, H. M.

AU - Lin, Y. H.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Hearing loss would seriously degrade a subject's speech perception, thereby affecting the development of articulation ability. Assistive listening devices such as hearing aids or cochlear implants could help subjects with hearing loss develop their speech perception. To facilitate this process, speech-language patholo-gists (SLPs) provide speech-perception training that can increase the subject's ability to distinguish one phoneme from another. In clinical practice, they manually enhance the acoustic cues and use this information therein to teach a subject the differences between two phonemes. However, it is a time-consuming and expensive process. In this study, an objective identification of spectral distinctiveness is proposed to find the acoustic cues between two phonemes. SLPs then could use it to facilitate the speech-perception training process. Mel-frequency cep-strum coefficients (MFCCs) are selected to accurately represent the characteristics of acoustic signal. To deal the mismatch between two phonemes in time domain, the Viterbi algorithm is integrated to find a best matching condition. In order to estimate the spectral similarity, the speech signal is decomposed into different frequency bands. For each bands, MFCCs are also applied to represent the characteristic of filtered speech signals. According to the best matching condition, the spectral distinctiveness of different bands between two phonemes could be easily estimated by using Euclidean metrics. Finally, the morphological gradient is adopted to find the sections of spectral distinctiveness. To evaluate the correction of proposed approach, the speech signal of identified spectral distinctiveness was manually manipulated, and then the manipulated speeches are evaluated by a close-set detection evaluation methodology. The experimental results demonstrated that our approach is able to identify a suitable spectral distinctiveness.

AB - Hearing loss would seriously degrade a subject's speech perception, thereby affecting the development of articulation ability. Assistive listening devices such as hearing aids or cochlear implants could help subjects with hearing loss develop their speech perception. To facilitate this process, speech-language patholo-gists (SLPs) provide speech-perception training that can increase the subject's ability to distinguish one phoneme from another. In clinical practice, they manually enhance the acoustic cues and use this information therein to teach a subject the differences between two phonemes. However, it is a time-consuming and expensive process. In this study, an objective identification of spectral distinctiveness is proposed to find the acoustic cues between two phonemes. SLPs then could use it to facilitate the speech-perception training process. Mel-frequency cep-strum coefficients (MFCCs) are selected to accurately represent the characteristics of acoustic signal. To deal the mismatch between two phonemes in time domain, the Viterbi algorithm is integrated to find a best matching condition. In order to estimate the spectral similarity, the speech signal is decomposed into different frequency bands. For each bands, MFCCs are also applied to represent the characteristic of filtered speech signals. According to the best matching condition, the spectral distinctiveness of different bands between two phonemes could be easily estimated by using Euclidean metrics. Finally, the morphological gradient is adopted to find the sections of spectral distinctiveness. To evaluate the correction of proposed approach, the speech signal of identified spectral distinctiveness was manually manipulated, and then the manipulated speeches are evaluated by a close-set detection evaluation methodology. The experimental results demonstrated that our approach is able to identify a suitable spectral distinctiveness.

UR - http://www.scopus.com/inward/record.url?scp=84896675533&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896675533&partnerID=8YFLogxK

M3 - Paper

SP - 195

EP - 198

ER -

Chen YJ, Lee MD, Wu J-L, Yang HM, Lin YH. An objective identification of spectral distinctiveness on acoustic cue to subjects with hearing loss. 2014. Paper presented at 2nd International Conference on Innovation, Communication and Engineering, ICICE 2013, Qingdao, China.