並列摘要
Since the voice conversion (VC) technology becomes widely used, there have been a lot of methods proposed by researchers in recent years. In this paper, we introduce the various applications and four kinds of performance evaluation approaches for VC. Furthermore, we also give an overall review of VC kernel methods and conclude with some viewpoints. This study involves four popular kernel methods, which are vector quantization, Gaussian mixture model, artificial neural network, and hidden Markov model. The principle and the property of each method are elaborated in this paper.
被引用紀錄
Hsiao, C. J. (2006). 中文語音轉換在混合激發線性預測語音編碼器上之實現 [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU.2006.01155
延伸閱讀
- 李振宇、闕壯華（2011）。多角色語音合成技術的文獻回顧。電腦與通訊，(139)，60-65。https://doi.org/10.29917/CCLTJ.201106.0012
- 林政源、黃柏凱、鄭志民、郭志忠（2010）。表達式語音合成之文獻回顧。電腦與通訊，(133)，81-87。https://doi.org/10.29917/CCLTJ.201006.0015
- 米建國（2013）。語意轉換的真理論。哲學與文化，40(9)，149-167。https://www.airitilibrary.com/Article/Detail?DocID=10158383-201309-201310090031-201310090031-149-167
- 林義聖（2021）。End-to-End Exemplar-Based Any-to-Any Voice Conversion〔碩士論文，國立臺灣大學〕。華藝線上圖書館。https://doi.org/10.6342/NTU202101228
- 徐宛伶、孟令夫、張維修（2011）。A Review of Redundancy Gain。人因工程學刊，13(1)，27-39。https://doi.org/10.6273/JES.2011.13(1).03