人工智慧讓人看到科技和語音結合的無限可能。
基本介紹
- 外文名:Deep Speech 2
- 類別:語音識別系統
人工智慧讓人看到科技和語音結合的無限可能。
百度近日在美國康奈爾大學圖書館的arXiv.org網站上發表論文稱,已開發出了一種新的語音識別系統Deep Speech,準確率超過了蘋果、谷歌的產品。產品特點 百度首席科學家吳恩達以及由Awni Hannun領導的10人研究團隊在美國康奈爾大學圖書館網站上稱,他們已經開發出了一種新的,更為準確的語音識別系統Deep Speech,該系統使用...
SwiftScribe是百度矽谷實驗室(SVAIL)研發的人工智慧網頁套用,可以把音頻資料轉錄成文字。2017年3月,百度推出音頻轉文本套用,暫時免費。只測試英文語音,其他語音尚未推出。發展歷程 2014年,百度的首席科學家吳恩達帶著一個10人的團隊開發 Deep Speech——一套語音識別系統。當時的研究重點在怎么提高嘈雜環境下的英語...
(2) Unsupervised Prosodic Labeling of Speech Synthesis Databases Using Context-Dependent HMMs - IEICE Transactions on Information and Systems - 2014 - vol.E97-D, no.6 (3) Improving deep neural networks for LVCSR using dropout and shrinking structure - ICASSP. FLORENCE, ITALY:IEEE - 2014.5 - ...
Xiang Hao, Shixue Wen, Xiangdong Su, Yun Liu, Guanglai Gao, Xiaofei Li:Sub-Band Knowledge Distillation Framework for Speech Enhancement. INTERSPEECH 2020: 2687-2691 Hao Li, DeLiang Wang, Xueliang Zhang, Guanglai Gao:Frame-Level Signal-to-Noise Ratio Estimation Using Deep Learning. INTERSPEECH ...
Chuang Ding, Pengcheng Zhu, Lei Xie, Dongmei Jiang and Zhonghua Fu, "Speech-Driven Head Motion Synthesis Using Neural Networks,"Interspeech, Singapore, 14-18, September 2014 Chenglin Xu, Lei Xie, Guangpu Huang, Xiong Xiao, Eng Siong Chng and Haizhou Li, "A Deep Neural Network Approach for...
(2) Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data, IEEE ACM Trans. Audio Speech Lang. Process., 2021, 第 4 作者 (3) Deep Time Delay Neural Network for Speech Enhancement with Full Data Learning, ISCSLP, 2021, 第 5 作者 (4) Towards Fine-...
Zhehuai Chen, Yimeng Zhuang, Yanmin Qian and Kai Yu. Phone Synchronous Speech Recognition with CTC Lattices. IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 25, no. 1, 86-97, 2017.Tian Tan, Yanmin Qian and Kai Yu. Cluster Adaptive Training for Deep Neural Network ...