Copyright © 2008 The Institute of Electronics, Information and Communication Engineers
Regular Section -- Papers -- Speech and Hearing |
Robust Speech Spectra Restoration against Unspecific Noise Conditions for Pitch Detection
1 The authors are with the Graduate School of Information Science and Technology, Hokkaido University, Sapporo-shi, 060-0814 Japan. E-mail: steven{at}csm.ist.hokudai.ac.jp
This paper proposes a new algorithm named Adaptive Running Spectrum Filtering (ARSF) to restore the amplitude spectra of speech corrupted by additive noises. Based on the pre-hand noise estimation, adaptive filtering is used in speech modulation spectra according to the noise conditions. The periodic structures in the amplitude spectra are kept against noise distortion. Since the amplitude spectral structures contain the information of fundamental frequency, which is the inverse of pitch period, ARSF algorithm is added into robust pitch detection to increase the accuracy. Compared with the conventional methods, experimental results show that the proposed method significantly improves the robustness of pitch detection against noise conditions with several types and SNRs.
Key Words: ARSF, noise robust, pitch detection, modulation spectra
Manuscript received April 2, 2007. Manuscript revised July 24, 2007.
Reference
[1] C.A. McGonegal, L.R. Rabiner, and A.E. Rosenberg, "A semiautomatic pitch detector (SAPD)," IEEE Trans. Acoust. Speech Signal Process., vol.ASSP-23, no.6, pp.570–574, Dec. 1975. [2] M. Kazama and M. Tohyama, "Estimation of speech components by ACF analysis in a noisy environment," J. Sound and Vibration, vol.241, no.1, pp.41–52, 2001. [3] W.J. Hess, Pitch and voicing determination, advances in speech signal processing, in Advances in Speech Signal Processing, ed., S. Furui and M.M. Sondhi, Marcel Dekker, New York. 1992. [4] M.M. Sondhi, "New methods of pitch extraction," IEEE Trans. Audio and Electroacoustics, vol.AU-16, no.2, pp.262–266, June 1968. [5] L.R. Rabiner, M.J. Cheng, A.E. Rosenberg, and C.A. McGonegal, "A comparative performance study of several pitch detection algorithms," IEEE Trans. Acoust. Speech Signal Process., vol.ASSP-24, no.5, pp.399–418, Oct. 1976. [6] T. Shimamura and H. Takagi, "Noise-robust fundamental frequency extraction method based on exponentiated band-limited amplitude spectrum," 47th IEEE International Midwest Symposium on Circuits and Systems, no.2, pp.II-141–II-148, 2004. [7] H. Kobayashi and T. Shimamura, "An extraction method of fundamental frequency using clipping and band limitation on log spectum," IEICE Trans. Fundamentals (Japanese Edition), vol.J82-A, no.7 pp.1115–1122, July 1999. [8] N. Hayasaka, N. Wada, Y. Miyanaga, and N. Hataoka, "Running spectrum filter for robust speech recognition," IEICE Technical Report, CAS2003-6, VLD2003-16, DSP2003-36, 2003. [9] Q. Zhu, N. Ohtsuki, Y. Miyanaga, and N. Yoshida, "Noise-robust speech analysis using running spectrum filtering," IEICE Trans. Fundamentals, vol.E88-A, no.2, pp.541–548, Feb. 2005. [10] X. Xu, N. Hayasaka, Q. Zhu, and Y. Miyanaga, "Noise robust chinese speech recognition system for isolate words," International Workshop on Nonlinear Signal and Image Processing 2005, no.1, pp.420–425, 2005. [11] X. Xu and Y. Miyanaga, "A robust pitch detection in noisy speech with band-pass filtering on modulation spectra," International Symposium on Communications and Information Technologies 2005, no.1, pp.266–269, 2005.
CiteULike 
Connotea 
Del.icio.us What's this?
This Article 
Abstract
Full Text (PDF)
Alert me when this article is cited
Alert me if a correction is posted
Services
Email this article to a friend
Similar articles in this journal
Alert me to new issues of the journal
Add to My Personal Archive
Download to citation manager
Request Permissions
Google Scholar
Articles by XU, X.
Articles by MIYANAGA, Y.
Search for Related Content
Social Bookmarking
What's this?