arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1603.09643cs.CLcs.LGcs.NEstat.ML
收藏

用于语音和说话人识别的多任务递归模型

Multi-task Recurrent Model for Speech and Speaker Recognition

Center for Speech and Language Technologies, Research Institute of Information Technology, Tsinghua University(清华大学信息技术研究院语音与语言技术中心);Tsinghua National Laboratory for Information Science and Technology(清华信息科学与技术国家实验室);Chengdu Institute of Computer Applications, Chinese Academy of Sciences(中国科学院成都计算机应用研究所)

Zhiyuan Tang, Lantian Li, Dong Wang

摘要:

虽然语音和说话人识别高度相关,但它们一直被视为两个独立的任务,并由两个社区进行研究。这当然不是人们的行为方式:我们同时解读语音内容和说话者的特征。本文提出了一个统一的模型,同时进行语音和说话人识别。该模型基于一个统一的神经网络,其中一个任务的输出被馈送到另一个任务的输入,从而导致多任务递归网络。实验表明,联合模型在两个任务上都优于特定任务模型。

英文摘要:

Although highly correlated, speech and speaker recognition have been regarded as two independent tasks and studied by two communities. This is certainly not the way that people behave: we decipher both speech content and speaker traits at the same time. This paper presents a unified model to perform speech and speaker recognition simultaneously and altogether. The model is based on a unified neural network where the output of one task is fed to the input of the other, leading to a multi-task recurrent network. Experiments show that the joint model outperforms the task-specific models on both the two tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑