6月4日，英国伯明翰大学电子电气与计算机工程系系主任Martin Russell教授受邀访问语音及语言信息处理国家工程实验室并在科技实验西楼第二会议室做了一场题为“Speech technologies for children”的学术报告。报告会由语音及语言信息处理国家工程实验室Ian Mcloughlin 教授主持。科大感兴趣的师生聆听了本次报告。

报告会上，Martin教授就儿童的语音识别技术展开了一系列的阐释。他表示儿童是语音科技在教育娱乐方面应用的最大潜在用户群。比如，在互动朗读、发音辅导中，儿童的语音识别是其发挥作用的关键。然而，自动识别儿童说话是十分困难的。据此，Martin教授阐述了儿童语音识别之所以困难的生理学及其他方面因素，并且介绍了至今为止已提出的解决方案。接着，Martin教授还就其相关的技术进展情况进行了集中论述，其中包括目前已经在儿童语音识别领域出现的“说话人识别”“性别识别”“年龄识别”等。

Martin教授图文并茂的宣讲引起了在场同学极大的兴趣与热烈的掌声。整场报告会气氛活跃，在报告后Martin教授与会师生对共同关心的问题再次进行了探讨。

简历：

Martin Russell is Professor of Information Engineering and formerly Head of the School of Electronic, Electrical and Computer Engineering at the University of Birmingham. He has a BSc (1977) and PhD (1981) in mathematics.  He is a Fellow of the Institute of Mathematics and its Applications, a Chartered Mathematician, a member of the IEEE, a member of the International Speech Communication Association (ISCA) and chair of the ISCA Special Interest Group on Speech and Language Technology in Education.  His current research projects cover a range of topics in speech recognition, including speech recognition by synthesis,  the effects of language acquisition in children on automatic speech recognition, the implications of regional accents for speech recognition, and  the EU CogWatch project on stroke rehabilitation.  He directs The Speech Ark Limited, a spin-out company which specialises in recording and annotating large corpora of British English speech. He has worked on a wide range of topics in speech and language science and technology and has published over 110 papers .  He has supervised 14 PhD students to successful completion and is currently working with 3 post-doctoral research fellows and 7 PhD students.