https://scholars.lib.ntu.edu.tw/handle/123456789/498369
標題: | Personalized acoustic modeling by weakly supervised multi-task deep learning using acoustic tokens discovered from unlabeled data | 作者: | Wei, C.-K. Chung, C.-T. HUNG-YI LEE LIN-SHAN LEE |
關鍵字: | deep neural network; multitask learning; speech adaptation; transfer learning; unsupervised learning | 公開日期: | 2017 | 起(迄)頁: | 5165-5169 | 來源出版物: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | 摘要: | It is well known that recognizers personalized to each user are much more effective than user-independent recognizers. With the popularity of smartphones today, although it is not difficult to collect a large set of audio data for each user, it is difficult to transcribe it. However, it is now possible to automatically discover acoustic tokens from unlabeled personal data in an unsupervised way. We therefore propose a multi-task deep learning framework called a phoneme-token deep neural network (PTDNN), jointly trained from unsupervised acoustic tokens discovered from unlabeled data and very limited transcribed data for personalized acoustic modeling. We term this scenario 'weakly supervised'. The underlying intuition is that the high degree of similarity between the HMM states of acoustic token models and phoneme models may help them learn from each other in this multi-task learning framework. Initial experiments performed over a personalized audio data set recorded from Facebook posts demonstrated that very good improvements can be achieved in both frame accuracy and word accuracy over popularly-considered baselines such as fDLR, speaker code and lightly supervised adaptation. This approach complements existing speaker adaptation approaches and can be used jointly with such techniques to yield improved results. © 2017 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85023743540&doi=10.1109%2fICASSP.2017.7953141&partnerID=40&md5=fd7a85ab4fcd6daaa74f73205b91b757 | ISSN: | 15206149 | DOI: | 10.1109/ICASSP.2017.7953141 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。