Two-Stage Frequency-Temporal Filtering for Effective Audio Fingerprinting of Sound Recordings
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Sound recordings are commonly distorted by channel and background noise. The performance of audio identification is mainly degraded by that noise. For an audio fingerprinting system, Haitsma and Kalker introduced a robust and efficient audio hashing scheme applying high-pass filtering (differentiation) to the frequency-temporal sequence of perceptual filter-bank energies. However, the robustness of the audio fingerprinting scheme is still important in real noisy environments. This paper introduces some alternatives of frequency-temporal filtering for effective audio fingerprinting of sound recordings in real environments. As the alternative to frequency filtering, a type of band-pass filter, instead of a high-pass filter, is used to enhance robustness to background noise in a real situation. As the alternative to temporal filtering, RASTA, instead of a high-pass filter, is used for normalizing sound recording conditions. As well, this paper introduces a two-stage audio fingerprinting scheme to achieve synergy of the combination of frequency-temporal filtering. Experimental results show that the proposed method is effective for sound recordings in real environments.
Abstract
Sound recordings are commonly distorted by channel and background noise. The performance of audio identification is mainly degraded by that noise. For an audio fingerprinting system, Haitsma and Kalker introduced a robust and efficient audio hashing scheme applying high-pass filtering (differentiation) to the frequency-temporal sequence of perceptual filter-bank energies. However, the robustness of the audio fingerprinting scheme is still important in real noisy environments. This paper introduces some alternatives of frequency-temporal filtering for effective audio fingerprinting of sound recordings in real environments. As the alternative to frequency filtering, a type of band-pass filter, instead of a high-pass filter, is used to enhance robustness to background noise in a real situation. As the alternative to temporal filtering, RASTA, instead of a high-pass filter, is used for normalizing sound recording conditions. As well, this paper introduces a two-stage audio fingerprinting scheme to achieve synergy of the combination of frequency-temporal filtering. Experimental results show that the proposed method is effective for sound recordings in real environments.
참고문헌 (18)
- J. Oostveen, "Feature Extraction and a Database Strategy for Video Fingerprinting", LNCS, 2314, pp.117~128 (2002)
- V. Venkatachalam, "Automatic Identification of Sound Recordings", IEEE Signal Processing Magazine, pp.92~99 (2004)
- A Highly Robust Audio Fingerprinting System, "J. Haitsma", Proc, 107~115, pp.ISMIR 2002 (2002)
- C. Burges, "Distortion discriminant analysis for audio fingerprinting", IEEE Trans. Speech and Audio Processing, 11(3), pp.165~174 (2003)
- M. L. Miller, "Audio Fingerprinting: Nearest neighbor search in high-dimensional binary space", IEEE Multimedia Signal Processing Workshop, pp.182~185 (2002)
- M. K. Mihcak, "A Perceptual Audio Hashing Algorithm: A Tool for Robust Audio Identification and Information Hiding", LNCS, 2137, pp.51~65 (2001)
- E. Allamanche, "AudioID: Towards Content-Based Identification of Audio Material" (2001), Proc. AES Convention
- 박만수, "실제 잡음 환경에 강인한 오디오 핑거프린팅 기법", Telecommunications Review, 16(3), pp.435~446 (2006), SK텔레콤
- M. Park, "Frequency Filtering for a Highly Robust Audio Fingerprinting Scheme in a Real-Noise Environment", IEICE Trans. Information and Systems, E89-D(7), pp.2324~2327 (2006)
- M. Park, "Frequency- Temporal Filtering for a Robust Audio Fingerprinting Scheme in Real-Noise Environments", ETRI J, 28(4), pp.509~512 (2006)
- J. Chen, "Cepstrum Derived from Differentiated Power Spectrum for Robust Speech Recognition", Speech Communication, 41, pp.469~484 (2003)
- Ho-Young Jung, "Filtering of Filter-Bank Energies for Robust Speech Recognition", ETRI Journal, 26(3), pp.273~276 (2004), 한국전자통신연구원
- C. Nadeu, "Time and Frequency Filtering of Filter-Bank Energies for Robust HMM Speech Recognition", Speech Communication, 34, pp.93~114 (2001)
- Compensation for the effect of the communication channel in the auditory-like analysis of speech (RASTA-PLP), "H. Hermansky", 1367~1370, pp.EUROSPEECH-91 (1991)
- Cepstral channel normalization techniques for HMM-based speaker verification, "A. Rosenberg", Proc, 1835~1838, pp.ICSLP-94 (1994)