Browse > Article
http://dx.doi.org/10.7776/ASK.2012.31.3.179

Noise Spectrum Estimation Using Line Spectral Frequencies for Robust Speech Recognition  

Jang, Gil-Jin (Ulsan National Institute of Science and Technology (UNIST))
Park, Jeong-Sik (Mokwon University)
Kim, Sang-Hun (Speech and Language Information Research Department Electronics and Telecommunications Research Institute)
Publication Information
The Journal of the Acoustical Society of Korea / v.31, no.3, 2012 , pp. 179-187 More about this Journal
Abstract
This paper presents a novel method for estimating reliable noise spectral magnitude for acoustic background noise suppression where only a single microphone recording is available. The proposed method finds noise estimates from spectral magnitudes measured at line spectral frequencies (LSFs), under the observation that adjacent LSFs are near the peak frequencies and isolated LSFs are close to the relatively flattened valleys of LPC spectra. The parameters used in the proposed method are LPC coefficients, their corresponding LSFs, and the gain of LPC residual signals, so it suits well to LPC-based speech coders.
Keywords
Line spectral frequencies (LSF); Noise suppression; Speech recognition;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Tom Backstrom and Carlo Magi, "Properties of line spectrum pair polynomials -- a review," Signal Processing, vol. 86, pp. 3286-3298, 2006.   DOI   ScienceOn
2 Martin Cooke and Te-Won Lee, "Speech separation challenge," INTERSPEECH, 2006.
3 Steve Young, Gunnar Evermann, , Mark Gales, Thomas Hain, Dan Kershaw, Xun-ying (Andrew) Liu, Gareth Moore, Julian Odell, Dave Ollason, Dan Povey, Valtcho Valtchev, and Phil Woodland, "Hidden Markov model toolkit (HTK) version 3.4," December 2006.
4 Telecommunications Industry Association (TIA), "Enhanced variable rate codec, speech service option 3 for wideband spread spectrum digital systems," Tech. Rep., TIA/EIA/IS-127, September 1996.
5 3rd Generation Partnership Project, "Amr speech codec," Tech. Rep., 3GPP TS 26.071, V6.0.0, December 2004.
6 European Telecommunications Standards Institute (ETSI), "Speech processing, transmission and quality aspects (stq); distributed speech recognition; advanced frontend feature extraction algorithm; compression algorithm," Tech. Rep., ES 202 050 v1.1.1, October 2002.
7 David Pearce and Hans-Günter Hirsch, "The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy condition," in Proc. ICSLP, Beijing, China, October 2000.
8 A. Kindoz and Ahmet M. Kondoz, Digital Speech; Coding for Low Bit Rate Communication Systems, John Wiley & Sons, Inc., New York, USA, 1994.
9 Mi Suk Lee, Hong Kook Kim, Seung Ho Choi, and Hwang Soo Lee, "On the use of LSF intermodel interlacing property for spectral quantization," in Proc. 1999 IEEE Workshop on Speech Coding, June 1999, pp. 43-45.
10 S. F. Boll, "Suppression of acoustic noise in speech using spectral subtraction," IEEE Transactions on Acoustics, Speech and Signal Processing, vol. 27, no. 2, pp. 113-120, 1979.   DOI
11 Mi Suk Lee, Hong Kook Kim, and Hwang Soo Lee, "A new distortion measure for spectral quantization based on the LSF intermodel interlacing property," Speech Communication, vol. 35, no. 3-4, pp. 191-202, October 2001.   DOI   ScienceOn
12 Peter Kabal and Ravi Prakash Ramachandran, "The computation of line spectral frequencies using chebyshev polynomials," IEEE Trans. Acoustics, Speech, Signal Processing, vol. 34, no. 6, pp. 1419-1426, December 1986.   DOI