광대역 음성에 대한 프레임내 잔차 벡터 양자화에 있어서 모델 복잡도와 성능 사이의 교환관계Trade-off between Model Complexity and Performance in Intra-frame Predictive Vector Quantization of Wideband Speech
- Other Titles
- Trade-off between Model Complexity and Performance in Intra-frame Predictive Vector Quantization of Wideband Speech
- Authors
- 송근배; 한헌수
- Issue Date
- Mar-2010
- Publisher
- 한국로봇학회
- Keywords
- Bandwidth Extension; Wideband Speech; Gaussian Mixture Model; Hidden Markov Model
- Citation
- 로봇학회 논문지, v.5, no.1, pp.70 - 76
- Journal Title
- 로봇학회 논문지
- Volume
- 5
- Number
- 1
- Start Page
- 70
- End Page
- 76
- URI
- http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/14866
- ISSN
- 1975-6291
- 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.
- Files in This Item
-
Go to Link
- Appears in
Collections - College of Information Technology > ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/14866)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.