i-manager Publications

Development of Speech Corpora for Speaker Recognition Systems

Piyush Lotia*, M.R. Khan**

* Research Scholar, Electronics and Telecommunication CSVTU Bhilai.

** Principal, New Government Engineering College Raipur.

Periodicity:April - June'2011
DOI : https://doi.org/10.26634/jee.4.4.1455

Abstract

Automatic Speaker Recognition (ASR) refers to the task of identifying a person based on his or her voice with the help of machines. It has been predicted that telephone-based services with integrated speech recognition, speaker recognition, and language recognition will supplement or even replace human-operated telephone services in the future. The main aim of this project is speaker identification, which consists of comparing a speech signal from an unknown speaker to a database of known speaker. The speaker identification is the process of determining which registered speaker provides a given speech. On the other hand, speaker verification is the process of rejecting or accepting the identity claim of a speaker Results of ASR are highly dependent on database. In this paper, a methodology and a typical experimental setup used for development of corpora for various tasks in the text-independent speaker identification in different Indian languages, viz Hindi ,English and Gujrati have been described. Finally This paper describes efforts to create corpora to support and evaluate systems that perform speaker recognition where channel and language may vary.

Keywords

Data collection, Corpus Design

How to Cite this Article?

Piyush Lotia and M.R. Khan (2011). Development of Speech Corpora for Speaker Recognition Systems. i-manager’s Journal on Electrical Engineering, 4(4), 19-25. https://doi.org/10.26634/jee.4.4.1455

References

[1]. Doddington, G. (1998). “Speaker Recognition Evaluation and Methodology: An Overview and Perspective,” Workshop on Speaker Recognition and its Commercial and Forensic Applications (RLA2C), Avignon, France, April 20-23, pp. 60-66.

[2] .NIST Speaker Recognition Evaluation Plans.http://www.nist.gov/speech/test.html.

[3] .European Lang Resources Assoc . http://www.icp.grenet.fr/ELRA.

[4] .Linguistic Data Consortium . http://www.ldc.upenn.edu/.

[5]. Oregon Graduate Institute. http://cslu.cse.ogi.edu/

[6]. Patil, H. A., & Basu, T. K. (2004). Speech corpus for text or language independent speaker recognition in Indian languages, Addendum to the lecture compendium. In Proceedings of National symposium on morphology, phonology and language engineering, SIMPLE' 04, IIT Kharagpur, India, pp. A1–A4,March19–21.

[7]. Atal, B. S., &Hanuaer, S. L. (1971). Speech analysis and synthesis by linear prediction of the speech wave. Journal of the Acoustical Society of America,50, pp 637–655.

[8]. Linguistic Data Consortium for Indian Languages. (2008).http://www.ldcil.org.

[9]. Kersta, L. G. (1962). Voiceprint identification. Nature, 196(4861),1253–1257 (29 December).

[10]. Reynolds, D. (1996), “The Effects of Handset Variability on Speaker Recognition Performance: Experiment on the Switchboard Corpus,”ICASSP, May, pp.113-116.

[11]. Li, K. P., & Wrench, E. H. Jr. (1983). Text-independent speaker recognition with short utterances. In Proceedings of international conference on acoustics, speech, and signal processing, ICASSP'83, Boston, MA (pp. 555–558).

[12]. Patil, H. A., & Basu, T. K. (2004). Multilingual speech corpus design for speaker identification in Indian languages. In International workshop on standardization of speech database, oriental COCOSDA'04, Noida, Delhi, India, pp17–19 November.

[13]. Patil, H. A., & Basu, T. K. (2009). LP Spectra vs. Mel Spectra for identification of professional mimics in Indian languages. International Journal of Speech Technology. doi:10.1007/s10772-009-9031y.

[14]. S S Agrawal, K Samudravijaya, Karunesh Arora, (2004). “Text and Speech Corpora Development in Indian Languages”, Proceedings of ICSLT-O-COCOSDA New Delhi, India.

[15]. Ed. K. Samudravijaya (2003). et al., Proc. Work on Spoken Language Processing, TIFR & ISCA, Jan 9-11, Mumbai.

If you have access to this article please login to view the article or kindly login to purchase the article

Single Article

	North Americas,UK, Middle East,Europe		India	Rest of world
	USD	EUR	INR	USD-ROW
Online	15	15

ADD TO CART

Options for accessing this content:

If you would like institutional access to this content, please recommend the title to your librarian.
If you already have i-manager's user account: Login above and proceed to purchase the article.
New Users: Please register, then proceed to purchase the article.