광대역 음성에 대한 프레임내 잔차 벡터 양자화에 있어서 모델 복잡도와 성능 사이의 교환관계
Trade-off between Model Complexity and Performance in Intra-frame Predictive Vector Quantization of Wideband Speech
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This paper addresses a design issue of “model complexity and performance trade-off” in the application of bandwidth extension (BWE) methods to the intra-frame predictive vector quantization problem of wideband speech. It discusses model-based linear and non-linear prediction methods and presents a comparative study of them in terms of prediction gain. Through experimentation, the general trend of saturation in performance (with the increase in model complexity) is observed. However, specifically, it is also observed that there is no significant difference between HMM and GMM-based BWE functions.
Abstract
This paper addresses a design issue of “model complexity and performance trade-off” in the application of bandwidth extension (BWE) methods to the intra-frame predictive vector quantization problem of wideband speech. It discusses model-based linear and non-linear prediction methods and presents a comparative study of them in terms of prediction gain. Through experimentation, the general trend of saturation in performance (with the increase in model complexity) is observed. However, specifically, it is also observed that there is no significant difference between HMM and GMM-based BWE functions.
참고문헌 (9)
- M. Nilsson, "Gaussian mixture model based mutual information between frequency bands in speech", ICASSP, pp.525~528 (2002)
- Y. Agiomyrgiannakis, "Conditional vector quantization for speech coding", IEEE Trans. Audio, Speech, Lang. Process., 15(2), pp.377~386 (2007)
- B. Geiser, "Backwards compatible wideband telephony in mobile networks: CELP watermarking and bandwidth extension", ICASSP, 통권 : 4, pp.533~536 (2007)
- P. Jax, "Bandwidth extension for speech In Audio Bandwidth Extension", pp.171~235 (2004), John Wiley & Sons
- K. -Y. Park, "Narrowband to wideband conversion of speech using GMM based transformation", ICASSP, 통권 : 3, pp.1843~1846 (2000)
- G.-B.Song, "A Study of HMM-based bandwidth extension of speech signals", Signal Processing, 89(10), pp.2036~2044 (2009)
- Linde Y, "An algorithm for vector quantizer design", IEEE Trans. Comm., 28(1), pp.84~95 (1980)
- P. Jax, "Artificial bandwidth extension of speech signals using MMSE estimation based on a hidden Markov model", ICASSP, 통권 : 1, pp.680~683 (2003)
- J. S. Garofolo, "DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus CD-ROM", NIST, ~ (1990)