User profiling through spoken utterances for user specific service

Minseok Keum; David K. Han; Hanseok Ko

User profiling through spoken utterances for user specific service

Minseok Keum, David K. Han, Hanseok Ko

School of Electrical Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

For providing user specific services in vehicle environment, we propose a speech based interface that identifies gender, age, and language of a user during speech utterances. For gender and age recognition, physiological factors are important discriminative information. However, for language recognition, phonotactics in addition to spectral information is exploited. All of the above schemes are evaluated using Mel-Frequency Cepstral Coefficient (MFCC) based features and Gaussian Mixture Models (GMM). We also evaluate the effectiveness of channel compensation techniques such as Cepstral Mean Subtraction (CMS) and RASTA filtering. As a conclusion we suggest that MFCC based feature can effectively be applied to the speech related recognition problems.

Original language	English
Publication status	Published - 2011
Event	5th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems, DSP 2011 - Kiel, Germany Duration: 2011 Sept 4 → 2011 Sept 7

Other

Other	5th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems, DSP 2011
Country/Territory	Germany
City	Kiel
Period	11/9/4 → 11/9/7

Keywords

Cepstral-Time Matrix (CTM)
Channel compensation
Gaussian Mixture Models (GMM)
Mel-Frequency Cepstral Coefficient (MFCC)
Speech user profiling

ASJC Scopus subject areas

Signal Processing
Automotive Engineering

Cite this

@conference{87b924c10cb94373bd72c0bc7d32900b,

title = "User profiling through spoken utterances for user specific service",

abstract = "For providing user specific services in vehicle environment, we propose a speech based interface that identifies gender, age, and language of a user during speech utterances. For gender and age recognition, physiological factors are important discriminative information. However, for language recognition, phonotactics in addition to spectral information is exploited. All of the above schemes are evaluated using Mel-Frequency Cepstral Coefficient (MFCC) based features and Gaussian Mixture Models (GMM). We also evaluate the effectiveness of channel compensation techniques such as Cepstral Mean Subtraction (CMS) and RASTA filtering. As a conclusion we suggest that MFCC based feature can effectively be applied to the speech related recognition problems.",

keywords = "Cepstral-Time Matrix (CTM), Channel compensation, Gaussian Mixture Models (GMM), Mel-Frequency Cepstral Coefficient (MFCC), Speech user profiling",

author = "Minseok Keum and Han, {David K.} and Hanseok Ko",

note = "Funding Information: This research work was supported in part by CNPq and CAPES Brazilian funding agencies and UGC-BSR Research Start-Up-Grant F.30-420/2018(BSR), UGC, India. M. Chand would like thank CSIR-NPL, New Delhi, India for using magneto-rheometer to carry out rheological measurements.; 5th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems, DSP 2011 ; Conference date: 04-09-2011 Through 07-09-2011",

year = "2011",

language = "English",

}

TY - CONF

T1 - User profiling through spoken utterances for user specific service

AU - Keum, Minseok

AU - Han, David K.

AU - Ko, Hanseok

N1 - Funding Information: This research work was supported in part by CNPq and CAPES Brazilian funding agencies and UGC-BSR Research Start-Up-Grant F.30-420/2018(BSR), UGC, India. M. Chand would like thank CSIR-NPL, New Delhi, India for using magneto-rheometer to carry out rheological measurements.

PY - 2011

Y1 - 2011

N2 - For providing user specific services in vehicle environment, we propose a speech based interface that identifies gender, age, and language of a user during speech utterances. For gender and age recognition, physiological factors are important discriminative information. However, for language recognition, phonotactics in addition to spectral information is exploited. All of the above schemes are evaluated using Mel-Frequency Cepstral Coefficient (MFCC) based features and Gaussian Mixture Models (GMM). We also evaluate the effectiveness of channel compensation techniques such as Cepstral Mean Subtraction (CMS) and RASTA filtering. As a conclusion we suggest that MFCC based feature can effectively be applied to the speech related recognition problems.

AB - For providing user specific services in vehicle environment, we propose a speech based interface that identifies gender, age, and language of a user during speech utterances. For gender and age recognition, physiological factors are important discriminative information. However, for language recognition, phonotactics in addition to spectral information is exploited. All of the above schemes are evaluated using Mel-Frequency Cepstral Coefficient (MFCC) based features and Gaussian Mixture Models (GMM). We also evaluate the effectiveness of channel compensation techniques such as Cepstral Mean Subtraction (CMS) and RASTA filtering. As a conclusion we suggest that MFCC based feature can effectively be applied to the speech related recognition problems.

KW - Cepstral-Time Matrix (CTM)

KW - Channel compensation

KW - Gaussian Mixture Models (GMM)

KW - Mel-Frequency Cepstral Coefficient (MFCC)

KW - Speech user profiling

UR - http://www.scopus.com/inward/record.url?scp=84899568489&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84899568489

T2 - 5th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems, DSP 2011

Y2 - 4 September 2011 through 7 September 2011

ER -

User profiling through spoken utterances for user specific service

Abstract

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this