Tools

LEADER 03243cam a2200505 i 4500

001 on1397376891;

003 OCoLC;

005 20260527041734.0;

006 m o d ;

007 cr unu||||||||;

008 230915s2023 ncua obm 000 0 eng d;

035 a| (OCoLC)1397376891;

090 a| TK7882.S65;

049 a| EREE;

100 1 a| Abueg, Abelson,e| author.?| UNAUTHORIZED;

245 12 a| A comparative study on MFCC, GFCC, BFCC, and CQCC spectral speech feature performance in x-vector clustering /c| by Abelson Abueg.;

264 1 a| [Greenville, N.C.] :b| [East Carolina University],c| 2023.;

300 a| 1 online resource (88 pages) :b| illustrations (some color);

336 a| textb| txt2| rdacontent;

337 a| computerb| c2| rdamedia;

338 a| online resourceb| cr2| rdacarrier;

347 a| text fileb| PDFc| 1.741 MB2| rda;

538 a| System requirements: Adobe Reader.;

538 a| Mode of access: World Wide Web.;

502 b| M.S.c| East Carolina Universityd| 2023.;

500 a| Presented to the Faculty of the Department of Computer Science;

500 a| Advisor: Nasseh Tabrizi;

500 a| Title from PDF t.p. (viewed November 25, 2024).;

520 3 a| Speaker diarization plays a crucial role in accurately identifying speakers in audio or video streams with multiple speakers. However, the use of Mel-frequency cepstral coefficients (MFCC) as the default speaker feature has posed a significant limitation in speech processing research. Existing literature suggests a lack of research addressing this limitation. This thesis aims to fill this gap by exploring alternative speech features and conducting a comprehensive investigation of their performance in the clustering step of speaker diarization. By conducting a comparative analysis of various spectral features, including Gammatone Frequency Cepstral Coefficients (GFCC), Constant-Q Cepstral Coefficients (CQCC), and Bark Frequency Cepstral Coefficients (BFCC), this study trains four distinct x-vector embedding deep neural networks (DNNs) and evaluates their effectiveness using four clustering algorithms. The results highlight the potential of the investigated alternative spectral features to outperform MFCC, emphasizing the need to move beyond the default MFCC approach and encouraging further exploration of alternative speech features for enhancing speaker diarization and related speech-processing tasks.;

504 a| Includes bibliographical references.;

650 0 a| Speech processing systems.=| ^A50976;

650 0 a| Speaker diarization.=| ^A1477060;

653 a| spectral feature comparison;

653 a| x-vector;

653 a| DNN;

653 a| clustering;

700 1 a| Tabrizi, M. H. N.,e| degree supervisor.?| UNAUTHORIZED;

710 2 a| East Carolina University.b| Department of Computer Science.?| UNAUTHORIZED;

856 40 z| Access via ScholarShipu| http://hdl.handle.net/10342/13177;

994 a| C0b| ERE;

596 a| 1 4;

998 a| 6234547;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 6234547-1001l| JNETm| JOYNERr| Ys| Yt| JNE3ETDu| 9/15/2023x| ETDz| JERESOURCE;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 6234547-2001l| HSLELECm| HSLr| Ys| Yt| HEETDu| 9/15/2023x| ETDz| HERESOURCE;

A comparative study on MFCC, GFCC, BFCC, and CQCC spectral speech feature performance in x-vector clustering / by Abelson Abueg.

Author/creator	Abueg, Abelson author.
Other author	Tabrizi, M. H. N., degree supervisor.
Other author	East Carolina University. Department of Computer Science.
Format	Theses and dissertations
Publication	[Greenville, N.C.] : [East Carolina University], 2023.
Description	1 online resource (88 pages) : illustrations (some color)
Supplemental Content	Access via ScholarShip
Subjects	Speech processing systems. Speaker diarization.

Summary	Speaker diarization plays a crucial role in accurately identifying speakers in audio or video streams with multiple speakers. However, the use of Mel-frequency cepstral coefficients (MFCC) as the default speaker feature has posed a significant limitation in speech processing research. Existing literature suggests a lack of research addressing this limitation. This thesis aims to fill this gap by exploring alternative speech features and conducting a comprehensive investigation of their performance in the clustering step of speaker diarization. By conducting a comparative analysis of various spectral features, including Gammatone Frequency Cepstral Coefficients (GFCC), Constant-Q Cepstral Coefficients (CQCC), and Bark Frequency Cepstral Coefficients (BFCC), this study trains four distinct x-vector embedding deep neural networks (DNNs) and evaluates their effectiveness using four clustering algorithms. The results highlight the potential of the investigated alternative spectral features to outperform MFCC, emphasizing the need to move beyond the default MFCC approach and encouraging further exploration of alternative speech features for enhancing speaker diarization and related speech-processing tasks.
General note	Presented to the Faculty of the Department of Computer Science
General note	Advisor: Nasseh Tabrizi
General note	Title from PDF t.p. (viewed November 25, 2024).
Dissertation note	M.S. East Carolina University 2023.
Bibliography note	Includes bibliographical references.
Technical details	System requirements: Adobe Reader.
Technical details	Mode of access: World Wide Web.

Availability

Library	Location	Call Number	Status	Item Actions
	Electronic Resources	Access Content Online	✔ Available

A comparative study on MFCC, GFCC, BFCC, and CQCC spectral speech feature performance in x-vector clustering / by Abelson Abueg.

Click here for more information about this title

Availability