research-article

Combining Evidences from Bark Scale and Mel Scale Warped Features for VTLN

Authors:

Shubham Sharma,

Hemant A. PatilAuthors Info & Claims

PerMIn '15: Proceedings of the 2nd International Conference on Perception and Machine Intelligence

Pages 133 - 136

https://doi.org/10.1145/2708463.2709042

Published: 26 February 2015 Publication History

Abstract

Vocal tract length normalization (VTLN) is a process of reducing the effects of VTL differences among speakers. In this paper, frequency warping based on Bark scale is presented to obtain VTL normalized features and Bark scale based features (BSBF) have been proposed. BSBFs are found to improve the accuracy of vowel recognition task by 1.05 % over MFCCs. A feature-level fusion of BSBFs with MFCCs performs better than MFCCs alone under matched and mismatched conditions in phoneme recognition.

References

[1]

L. R. Rabiner, Fundamentals of Speech Recognition. PTR Prentice Hall, 1993.

Digital Library

[2]

H. Wakita, "Normalization of vowels by vocal tract length and its applications to vowel identification," IEEE Trans. Acoust., Speech and Signal Process., vol. 25, no. 2, pp. 183--192, April 1977.

[3]

A. Andreou, T. Kamm, and J. Cohen, "Experiments in vocal tract length normalization," Proc. the CAIP Workshop: Frontiers in Speech Recognition II, 1944.

[4]

L. Lee and R. Rose, "A frequency warping approach to speaker normalization," in IEEE Trans. on Speech and Audio Process., vol. 6, no.1, pp. 49--60, 1998.

[5]

H. Gish and E. Eide, "A parametric approach to vocal tract length normalization," Inter. Conf. on Acoust., Speech and Signal Proc. (ICASSP), vol. 1, pp. 346--349, 1996.

Digital Library

[6]

S. Umesh, L. Cohen, N. Marinovik, and D. Nelson, "Scale transform in speech analysis," IEEE Trans. on Speech and Audio Process., vol. 7, no. 1, pp. 40--45, January, 1999.

[7]

A. Mertins and J. Rademacher, "Vocal tract length invariant features for automatic speech recognition," in Auto. Speech Recog. and Understanding workshop (ASRU), pp. 308--312, 2005.

[8]

S. Umesh, D. R. Sanand, and G. Praveen, "Speaker-invariant features for automatic speech recognition," in Int. Joint Conf. on Artificial Intelligence (IJCAI), pp. 1738--1743, 2007.

Digital Library

[9]

E. Zwicker, "Subdivision of the audible frequency range into critical bands (Frequenzgruppen)," J. of the Acoust. Soc. of Amer., vol. 33, no. 2, pp. 248--248, 1961.

[10]

E. Zwicker and E. Terhardt, "Analytical expressions for critical-band rate and critical bandwidth as a function of frequency," J. of the Acoust. Soc. of Amer., vol. 68, no. 5, pp. 1523--1525, Nov, 1980.

[11]

J. Garofolo et al. TIMIT Acoustic-Phonetic Continuous Speech Corpus LDC93S1, Philadelphia: Linguistic Data Consortium, 1993.

[12]

S. Umesh, L. Cohen, N. Marinovik and D. Nelson, "Frequency warping in speech," Proc. Int. Conf. Spoken Lang. Process., vol. 1, pp. 414--417, 1996.

[13]

J. O. Smith III and J. S. Abel, "Bark and ERB bilinear transforms," in Int. Conf. on Acoust., Speech and Signal Process (ICASSP), vol. 7, pp. 697--708, 1999.

[14]

H. A. Murty and B. Yegnanarayana, "Group delay functions and its applications in speech technology," Sadhana, vol. 36, no. Part 5, pp. 745--782, October 2011.

[15]

M. Trzos, "Frequency warping via warped linear prediction," in Telecomm. and Signal Process. (TSP), pp. 348--350, August, 2011.

[16]

L. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," in Proceedings of the IEEE, vol. 77, no.2, pp. 257--286, 1989.

[17]

S. B. Mermelstein and P. Davis, "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences," in IEEE Trans. Acoust., Speech and Signal Process., vol. 28, no. 4, pp. 357- 366, August 1980.

[18]

Cambridge University Engineering Department. The Hidden Markov Model Toolkit. {Available Online}. http://htk.eng.cam.ac.uk/ {Last accessed: 3rd June, 2014}.

Cited By

Tejaswini SSriraam NPradeep G. C. M. (2020)Identification of High Risk and Low Risk Preterm Neonates in NICUBiomedical and Clinical Engineering for Healthcare Advancement10.4018/978-1-7998-0326-3.ch007(119-140)Online publication date: 2020
https://doi.org/10.4018/978-1-7998-0326-3.ch007

Index Terms

Combining Evidences from Bark Scale and Mel Scale Warped Features for VTLN
1. Computing methodologies
  1. Artificial intelligence
    1. Natural language processing

Recommendations

Combining Evidences from Mel Cepstral and Cochlear Cepstral Features for Speaker Recognition Using Whispered Speech
TSD 2015: Proceedings of the 18th International Conference on Text, Speech, and Dialogue - Volume 9302

Whisper is an alternative way of speech communication especially when a speaker does not want to reveal the information other than the target listeners. Generally, speaker-specific information is present in both excitation source and vocal tract system. ...
Vocal Tract Length Normalization using a Gaussian mixture model framework for query-by-example spoken term detection
Abstract
A speech spectrum is known to be changed by the variations in the length of the vocal tract of a speaker. This is because of the fact that speech formants are inversely related to the vocal tract length (VTL). The process of ...
Regularized minimum variance distortionless response-based cepstral features for robust continuous speech recognition

We study the low-variance and robust features for speech recognition system on the AURORA-4 corpus.We propose to compute cepstral features from a regularized MVDR (RMVDR) spectral estimates, denoted as RMVDR-based Cepstral Coefficient (RMCC) features.A ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

PerMIn '15: Proceedings of the 2nd International Conference on Perception and Machine Intelligence

February 2015

269 pages

ISBN:9781450320023

DOI:10.1145/2708463

General Chair:
Sankar K. Pal
Indian Statistical Institute, Kolkata, India
,
Program Chairs:
Malay K. Kundu
Indian Statistical Institute, Kolkata, India
,
Santanu Chaudhury
Indian Institute of Technology, Delhi, India
,
Soma Mitra
CDAC, Kolkata, India
,
Debasis Mazumdar
CDAC, Kolkata, India

Copyright © 2015 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

Dept. of Science and Techn., Government of India: Department of Science and Technology, Government of India

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 26 February 2015

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

Department of Electronics and Information Technology, Ministry of Communications and Information Technology

Conference

PerMIn '15

PerMIn '15: 2nd International Conference on Perception and Machine Intelligence

February 26 - 27, 2015

West Bengal, Kolkata, India

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
73
Total Downloads

Downloads (Last 12 months)3
Downloads (Last 6 weeks)0

Reflects downloads up to 12 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Tejaswini SSriraam NPradeep G. C. M. (2020)Identification of High Risk and Low Risk Preterm Neonates in NICUBiomedical and Clinical Engineering for Healthcare Advancement10.4018/978-1-7998-0326-3.ch007(119-140)Online publication date: 2020
https://doi.org/10.4018/978-1-7998-0326-3.ch007

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents