HOME > Abstract

[PDF Full Text (345KB)]

Adaptive Kernel Function of SVM for Improving Speech/Music Classification of 3GPP2 SMV
Chungsoo Lim, and Joon-Hyuk Chang
Abstract :	Because a wide variety of multimedia services are provided through personal wireless communication devices, the demand for efficient bandwidth utilization becomes stronger. This demand naturally results in the introduction of the variable bitrate speech coding concept. One exemplary work is the selectable mode vocoder (SMV) that supports speech/music classification. However, because it has severe limitations in its classification performance, a couple of works to improve speech/music classification by introducing support vector machines (SVMs) have been proposed. While these approaches significantly improved classification accuracy, they did not consider correlations commonly found in speech and music frames. In this paper, we propose a novel and orthogonal approach to improve the speech/music classification of SMV codec by adaptively tuning SVMs based on interframe correlations. According to the experimental results, the proposed algorithm yields improved results in classifying speech and music within the SMV framework.
Key word :	SVM, SMV, speech/music classification algorithm.
DOI :	http://dx.doi.org/10.4218/etrij.11.0110.0780
Cite this :	Chungsoo Lim, and Joon-Hyuk Chang, "Adaptive Kernel Function of SVM for Improving Speech/Music Classification of 3GPP2 SMV," ETRI Journal, vol. 33, no. 6, Dec. 2011, pp. 871-879. http://dx.doi.org/10.4218/etrij.11.0110.0780
References :	1. 3GPP2 Spec., "Source-Controlled Variable-Rate Multimedia Wideband Speech Codec (VMR-WB), Service Option 62 and 63 for Spread Spectrum Systems," 3GPP2-C.S0052-A, vol. 1.0, Apr. 2005. 2. Y. Gao et al., "The SMV Algorithm Selected by TIA and 3GPP2 for CDMA Applications," Proc. IEEE Int. Conf. Acoustics, Speech, Signal Process., vol. 2, May 2002, pp. 709-712. 3. S.-K. Kim and J.-H. Chang, "Speech/Music Classification Enhancement for 3GPP2 SMV Codec Based on Support Vector Machine," IEICE Trans. Fundamentals Electron., Commun. Comput. Sci., vol. E92-A, no. 2, Feb. 2009. 4. X. Wang et al., "Infrared Human Face Auto Locating Based on SVM and a Smart Thermal Biometrics System," Proc. 6th Int. Conf. Intell. Syst. Design Appl., vol. 2, Oct. 2006, pp. 1066-1072. 5. A. Ganapathiraju, J.E. Hamaker, and J. Picone, "Applications of Support Vector Machines to Speech Recognition," IEEE Trans. Signal Process., vol. 52, no. 8, Aug. 2004, pp. 2348-2355. 6. L.-P. Bi et al., "New Heuristic for Determination Gaussian Kernel’s Parameter," Proc. Int. Conf. Mach. Learning Cybern., vol. 7, Aug. 2005, pp. 4299-4304. 7. S.S. Keerthi and C.-J. Lin, "Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel," Neural Comput., vol. 15, no. 7, July 2003, pp. 1667-1689. 8. J. Tian and L. Zhao, "Weighted Gaussian Kernel with Multiple Widths and Support Vector Classifications," Proc. Int Symp. Info. Eng. Electron. Commerce, May 2009, pp. 379-382. 9. N.E. Ayat, M. Cheriet, and C.Y. Suen, "Automatic Model Selection for the Optimization of SVM Kernels," Pattern Recognition, vol. 38, no. 10, Oct. 2005, pp. 1733-1745. 10. S.-K. Kim and J.-H. Chang, "Discriminative Weight Training for Support Vector Machine-Based Speech/Music Classification in 3GPP2 SMV Codec," IEICE Trans. Fundamentals of Electron., Commun. Comput. Sci., vol. E93-A, no. 1, Jan. 2010, pp. 316-319. 11. E. Scheirer and M. Slaney, "Construction and Evaluation of a Robust Multifeature Speech/Music Discriminator," Proc. IEEE Int. Conf. Acoustics, Speech, Signal Process., vol. 2, Apr. 1997, pp. 1331-1334. 12. S.C. Greer and A. Dejaco, "Standardization of the Selectable Mode Vocoder," Proc. IEEE Int. Conf. Acoustics, Speech, Signal Process., vol. 2, May 2001, pp. 953-956. 13. C.V. Goudar et al., "SMVLite: Reduced Complexity Selectable Mode vocoder," Proc. IEEE Int. Conf. Speech Signal Process., vol. 1, May 2006, pp. 701-704. 14. P. Vary and R. Martin, "Digital Speech Transmission: Enhancement, Coding and Error Concealment," Proc. IEEE Int. Conf. Acoutics, Speech, Signal Process., vol. 1, May 2006, pp. 701-704. 15. W.M. Fisher, G.R. Doddington, and K.M. Goudie-Marshall, "The DARPA Speech Recognition Research Database: Specifications and Status," Proc. DARPA Workshop Speech Recognition, Feb. 1986, pp. 93-99.
Reader   Evaluation :	Important   Innovative   Insightful   Useful

This article has been downloaded 1,629 times.

ETRI Journal Vol.33, No.6

Regular Papers

	Codebook-Based Precoding for SDMA-OFDMA with Spectrum Sharing
	Han-Shin Jo ETRI Journal, vol.33, no.6, Dec. 2011, pp.831-840 http://dx.doi.org/10.4218/etrij.11.0111.0078
	SNR Enhancement Algorithm Using Multiple Chirp Symbols with Clock Drift for Accurate Ranging
	Seong-Hyun Jang, Yeong-Sam Kim, Sang-Hun Yoon, and Jong-Wha Chong ETRI Journal, vol.33, no.6, Dec. 2011, pp.841-848 http://dx.doi.org/10.4218/etrij.11.0111.0013
	New Elements Concentrated Planar Fractal Antenna Arrays for Celestial Surveillance and Wireless Communications
	Ahmed Najah Jabbar ETRI Journal, vol.33, no.6, Dec. 2011, pp.849-856 http://dx.doi.org/10.4218/etrij.11.0111.0036
	Energy-Efficient Adaptive Dynamic Sensor Scheduling for Target Monitoring in Wireless Sensor Networks
	Jian Zhang, Cheng-dong Wu, Yun-zhou Zhang, and Peng Ji ETRI Journal, vol.33, no.6, Dec. 2011, pp.857-863 http://dx.doi.org/10.4218/etrij.11.0111.0027
	Characterization of a Hybrid Cu Paste as an Isotropic Conductive Adhesive
	Yong-Sung Eom, Kwang-Seong Choi, Seok-Hwan Moon, Jun-Hee PARK, Jong-Hyun LEE, and Jong-Tae Moon ETRI Journal, vol.33, no.6, Dec. 2011, pp.864-870 http://dx.doi.org/10.4218/etrij.11.0110.0520
	Adaptive Kernel Function of SVM for Improving Speech/Music Classification of 3GPP2 SMV
	Chungsoo Lim, and Joon-Hyuk Chang ETRI Journal, vol.33, no.6, Dec. 2011, pp.871-879 http://dx.doi.org/10.4218/etrij.11.0110.0780
	Low-Power Cool Bypass Switch for Hot Spot Prevention in Photovoltaic Panels
	Salvatore Pennisi, Francesco Pulvirenti, and Amedeo La Scala ETRI Journal, vol.33, no.6, Dec. 2011, pp.880-886 http://dx.doi.org/10.4218/etrij.11.0110.0744
	Polymer Dielectrics and Orthogonal Solvent Effects for High-Performance Inkjet-Printed Top-Gated P-Channel Polymer Field-Effect Transistors
	Kang-Jun Baeg, Dongyoon Khim, Soon-Won Jung, Jae Bon Koo, In-Kyu You, Yoon-Chae Nah, Dong-Yu Kim, and Yong-Young Noh ETRI Journal, vol.33, no.6, Dec. 2011, pp.887-896 http://dx.doi.org/10.4218/etrij.11.0111.0321
	A Hybrid Audio ΔΣ Modulator with dB-Linear Gain Control Function
	Yi-Gyeong Kim, Min-Hyung Cho, Bong Chan Kim, and Jong-Kee Kwon ETRI Journal, vol.33, no.6, Dec. 2011, pp.897-903 http://dx.doi.org/10.4218/etrij.11.0111.0293
	A Die-Selection Method Using Search-Space Conditions for Yield Enhancement in 3D Memory
	Joohwan Lee, Kihyun Park, and Sungho Kang ETRI Journal, vol.33, no.6, Dec. 2011, pp.904-913 http://dx.doi.org/10.4218/etrij.11.0111.0108
	Text-Independent Speaker Verification Using Variational Gaussian Mixture Model
	Mohammad Hossein Moattar, and Mohammad Mehdi Homayounpour ETRI Journal, vol.33, no.6, Dec. 2011, pp.914-923 http://dx.doi.org/10.4218/etrij.11.0110.0684
	Probabilistic Support Vector Machine Localization in Wireless Sensor Networks
	Reza Samadian, and Seyed Majid Noorhosseini ETRI Journal, vol.33, no.6, Dec. 2011, pp.924-934 http://dx.doi.org/10.4218/etrij.11.0110.0692
	Privacy-Preserving H.264 Video Encryption Scheme
	SuGil Choi, Jong-Wook Han, and Hyunsook Cho ETRI Journal, vol.33, no.6, Dec. 2011, pp.935-944 http://dx.doi.org/10.4218/etrij.11.0110.0644

Letters

	An Efficient Time-Frequency Representation for Parametric-Based Audio Object Coding
	Seungkwon Beack, Taejin Lee, Minje Kim, and Kyeongok Kang ETRI Journal, vol.33, no.6, Dec. 2011, pp.945-948 http://dx.doi.org/10.4218/etrij.11.0211.0007
	Simple Detection Based on Soft-Limiting for Binary Transmission in a Mixture of Generalized Normal-Laplace Distributed Noise and Gaussian Noise
	Sangchoon Kim ETRI Journal, vol.33, no.6, Dec. 2011, pp.949-952 http://dx.doi.org/10.4218/etrij.11.0211.0026
	A Novel Dual-Mode Bandpass Filter Based on a Defected Waveguide Resonator
	Xuehui Guan, Wei Fu, Haiwen Liu, Dal Ahn, and Jong Sik Lim ETRI Journal, vol.33, no.6, Dec. 2011, pp.953-956 http://dx.doi.org/10.4218/etrij.11.0211.0034
	Nash Bargaining Solution for RFID Frequency Interference
	Dongyul Lee, and Chaewoo Lee ETRI Journal, vol.33, no.6, Dec. 2011, pp.957-960 http://dx.doi.org/10.4218/etrij.11.0211.0037
	Enhanced FCME Thresholding for Wavelet-Based Cognitive UWB over Fading Channels
	Haleh Hosseini, Norsheila Fisal, and Sharifah Kamilah Syed-Yusof ETRI Journal, vol.33, no.6, Dec. 2011, pp.961-964 http://dx.doi.org/10.4218/etrij.11.0211.0046
	A 1.485-Gbit/s Video Signal Transmission System at Carrier Frequencies of 240 GHz and 300 GHz
	Tae Jin Chung, and Won-Hui Lee ETRI Journal, vol.33, no.6, Dec. 2011, pp.965-968 http://dx.doi.org/10.4218/etrij.11.0211.0053
	A Subthreshold CMOS RF Front-End Design for Low-Power Band-III T-DMB/DAB Receivers
	Seongdo Kim, Janghong Choi, Joohyun Lee, Bontae Koo, Cheonsoo Kim, Nakwoong Eum, Hyunkyu Yu, and Heebum Jung ETRI Journal, vol.33, no.6, Dec. 2011, pp.969-972 http://dx.doi.org/10.4218/etrij.11.0211.0055
	Efficient Maximum Power Tracking of Energy Harvesting Using a μController for Power Savings
	Sewan Heo, Yil Suk Yang, Jaewoo Lee, Sang-kyun Lee, and Jongdae Kim ETRI Journal, vol.33, no.6, Dec. 2011, pp.973-976 http://dx.doi.org/10.4218/etrij.11.0211.0149
	Subjective Listening Experiments on a Front and Rear Array-Based WFS System
	Jae-hyoun Yoo, Jeongil Seo, Hwan Shim, Hyunjoo Chung, Koeng-Mo Sung, and Kyeongok Kang ETRI Journal, vol.33, no.6, Dec. 2011, pp.977-980 http://dx.doi.org/10.4218/etrij.11.0210.0335
	Microstrip Lowpass Filter with Very Sharp Transition Band and Wide Stopband
	Mohsen Hayati, and Akram Sheikhi ETRI Journal, vol.33, no.6, Dec. 2011, pp.981-984 http://dx.doi.org/10.4218/etrij.11.0210.0493
	Dual-Transmission-Line Microstrip Equiripple Lowpass Filter with Sharp Roll-Off
	Vamsi Krishna Velidi, and Subrata Sanyal ETRI Journal, vol.33, no.6, Dec. 2011, pp.985-988 http://dx.doi.org/10.4218/etrij.11.0210.0497
	Fault Attack on a Point Blinding Countermeasure of Pairing Algorithms
	Jea Hoon Park, Gyo Yong Sohn, and Sang Jae Moon ETRI Journal, vol.33, no.6, Dec. 2011, pp.989-992 http://dx.doi.org/10.4218/etrij.11.0210.0483