Discrimination Effectiveness of Speech Cepstral Features

Amit S Malegaonkar; Aladdin Ariyaeeinia; Perasiriyan Sivakumaran; Surosh Pillay

Discrimination Effectiveness of Speech Cepstral Features

Amit S Malegaonkar, Aladdin Ariyaeeinia, Perasiriyan Sivakumaran, Surosh Pillay

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In this work, the discrimination capabilities of speech cepstra for text and speaker related information are investigated. For this purpose, Bhattacharya distance metric is used as the measure of discrimination. The scope of the study covers static and dynamic cepstra derived using the linear prediction analysis (LPCC) as well as mel-frequency analysis (MFCC). The investigations also include the assessment of the linear prediction-based mel-frequency cepstral coefficients (LP-MFCC) as an alternative speech feature type. It is shown experimentally that whilst contaminations in speech unfavourably affect the performance of all types of cepstra, the effects are more severe in the case of MFCC. Furthermore, it is shown that with a combination of static and dynamic features, LP-based mel-frequency cepstra (LP-MFCC) exhibit the best discrimination capabilities in almost all experimental cases.

Original language	English
Title of host publication	Biometrics and Identity Management, BIOID 2008
Publisher	Springer Nature Link
Pages	91-99
Number of pages	9
Volume	5372
ISBN (Electronic)	978-3-540-89991-4
ISBN (Print)	978-3-540-89990-7
Publication status	Published - May 2008

Publication series

Name	Lecture Notes in Computer Science
Volume	5372

Cite this

@inproceedings{61ad0a204190495ab81ad8e3f78d9f24,

title = "Discrimination Effectiveness of Speech Cepstral Features",

abstract = "In this work, the discrimination capabilities of speech cepstra for text and speaker related information are investigated. For this purpose, Bhattacharya distance metric is used as the measure of discrimination. The scope of the study covers static and dynamic cepstra derived using the linear prediction analysis (LPCC) as well as mel-frequency analysis (MFCC). The investigations also include the assessment of the linear prediction-based mel-frequency cepstral coefficients (LP-MFCC) as an alternative speech feature type. It is shown experimentally that whilst contaminations in speech unfavourably affect the performance of all types of cepstra, the effects are more severe in the case of MFCC. Furthermore, it is shown that with a combination of static and dynamic features, LP-based mel-frequency cepstra (LP-MFCC) exhibit the best discrimination capabilities in almost all experimental cases.",

author = "Malegaonkar, {Amit S} and Aladdin Ariyaeeinia and Perasiriyan Sivakumaran and Surosh Pillay",

year = "2008",

month = may,

language = "English",

isbn = "978-3-540-89990-7",

volume = "5372",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature Link",

pages = "91--99",

booktitle = "Biometrics and Identity Management, BIOID 2008",

address = "Netherlands",

}

TY - GEN

T1 - Discrimination Effectiveness of Speech Cepstral Features

AU - Malegaonkar, Amit S

AU - Ariyaeeinia, Aladdin

AU - Sivakumaran, Perasiriyan

AU - Pillay, Surosh

PY - 2008/5

Y1 - 2008/5

N2 - In this work, the discrimination capabilities of speech cepstra for text and speaker related information are investigated. For this purpose, Bhattacharya distance metric is used as the measure of discrimination. The scope of the study covers static and dynamic cepstra derived using the linear prediction analysis (LPCC) as well as mel-frequency analysis (MFCC). The investigations also include the assessment of the linear prediction-based mel-frequency cepstral coefficients (LP-MFCC) as an alternative speech feature type. It is shown experimentally that whilst contaminations in speech unfavourably affect the performance of all types of cepstra, the effects are more severe in the case of MFCC. Furthermore, it is shown that with a combination of static and dynamic features, LP-based mel-frequency cepstra (LP-MFCC) exhibit the best discrimination capabilities in almost all experimental cases.

AB - In this work, the discrimination capabilities of speech cepstra for text and speaker related information are investigated. For this purpose, Bhattacharya distance metric is used as the measure of discrimination. The scope of the study covers static and dynamic cepstra derived using the linear prediction analysis (LPCC) as well as mel-frequency analysis (MFCC). The investigations also include the assessment of the linear prediction-based mel-frequency cepstral coefficients (LP-MFCC) as an alternative speech feature type. It is shown experimentally that whilst contaminations in speech unfavourably affect the performance of all types of cepstra, the effects are more severe in the case of MFCC. Furthermore, it is shown that with a combination of static and dynamic features, LP-based mel-frequency cepstra (LP-MFCC) exhibit the best discrimination capabilities in almost all experimental cases.

M3 - Conference contribution

SN - 978-3-540-89990-7

VL - 5372

T3 - Lecture Notes in Computer Science

SP - 91

EP - 99

BT - Biometrics and Identity Management, BIOID 2008

PB - Springer Nature Link

ER -

Discrimination Effectiveness of Speech Cepstral Features

Abstract

Publication series

Fingerprint

Cite this