Natural Speech Technology

自然语音技术

• 批准号: EP/I031022/1
• 负责人: Steve Renals
• 金额: $ 794.6万
• 依托单位: University of Edinburgh
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2011
• 资助国家: 英国
• 起止时间: 2011 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FI031022%2F1
• 关键词: Natural; Speech; Technology

Humans are highly adaptable, and speech is our natural medium for informal communication. When communicating, we continuously adjust to other people, to the situation, and to the environment, using previously acquired knowledge to make this adaptation seem almost instantaneous. Humans generalise, enabling efficient communication in unfamiliar situations and rapid adaptation to new speakers or listeners. Current speech technology works well for certain controlled tasks and domains, but is far from natural, a consequence of its limited ability to acquire knowledge about people or situations, to adapt, and to generalise. This accounts for the uneasy public reaction to speech-driven systems. For example, text-to-speech synthesis can be as intelligible as human speech, but lacks expression and is not perceived as natural. Similarly, the accuracy of speech recognition systems can collapse if the acoustic environment or task domain changes, conditions which a human listener would handle easily. Research approaches to these problems have hitherto been piecemeal and as a result progress has been patchy. In contrast NST will focus on the integrated theoretical development of new joint models for speech recognition and synthesis. These models will allow us to incorporate knowledge about the speakers, the environment, the communication context and awareness of the task, and will learn and adapt from real world data in an online, unsupervised manner. This theoretical unification is already underway within the NST labs and, combined with our record of turning theory into practical state-of-the-art applications, will enable us to bring a naturalness to speech technology that is not currently attainable.The NST programme will yield technology which (1) approaches human adaptability to new communication situations, (2) is capable of personalised communication, and (3) takes account of speaker intention and expressiveness in speech recognition and synthesis. This is an ambitious vision. Its success will be measured in terms of how the theoretical development reshapes the field over the next decade, the takeup of the software systems that we shall develop, and through the impact of our exemplar interactive applications.We shall establish a strong User Group to maximise the impact of the project, with a members concerned with clinical applications, as well as more general speech technology. Members of the User Group include Toshiba, EADS Innovation Works, Cisco, Barnsley Hospital NHS Foundation Trust, and the Euan MacDonald Centre for MND Research. An important interaction with the User Group will be validating our systems on their data and tasks, discussed at an annual user workshop.

人类具有很高的适应性，语音是我们进行非正式交流的天然媒介。交流时，我们使用先前获得的知识来使这种适应似乎几乎瞬时地适应他人，情况和环境。人类概括，在不熟悉的情况下有效地沟通，并迅速适应新的演讲者或听众。当前的语音技术在某些受控的任务和领域效果很好，但远非自然，这是由于其获得有关人或情况知识，适应和概括的能力有限的结果。这说明了公众对语音驱动系统的不安反应。例如，文本到语音的综合可以像人类的言语一样可理解，但缺乏表达，也不被认为是自然的。同样，如果声学环境或任务域的变化，语音识别系统的准确性可能会崩溃，那么人类听众可以轻松处理的条件。迄今为止，解决这些问题的研究方法是零散的，因此进步是零散的。相比之下，NST将集中于新的言语识别和综合联合模型的综合理论发展。这些模型将使我们能够纳入有关说话者，环境，沟通环境和对任务意识的知识，并以在线，无监督的方式中学习和适应现实世界数据。 This theoretical unification is already underway within the NST labs and, combined with our record of turning theory into practical state-of-the-art applications, will enable us to bring a naturalness to speech technology that is not currently attainable.The NST programme will yield technology which (1) approaches human adaptability to new communication situations, (2) is capable of personalised communication, and (3) takes account of speaker intention and expressiveness in speech recognition and synthesis.这是一个雄心勃勃的愿景。它的成功将以理论开发在未来十年的重塑领域，我们将开发的软件系统的使用以及通过我们的示例互动应用的影响来衡量。我们应建立一个强大的用户群体，以最大程度地利用该项目的影响，与临床应用有关的成员以及更多的一般语音技术以及更多的一般语音技术。用户组的成员包括东芝，EADS创新工作，思科，Barnsley Hospital NHS基金会信托基金会和Euan MacDonald MND研究中心。与用户组的重要互动将是在年度用户研讨会上讨论的数据和任务上的系统。

项目成果

Multi-reference WER for evaluating ASR for languages with no orthographic rule

用于评估没有拼写规则的语言的 ASR 的多参考 WER

• 发表时间: 2015
• 期刊: Proc IEEE ASRU
• 作者: Ali A

Reactive accent interpolation through an interactive map application

通过交互式地图应用程序进行反应式重音插值

• 发表时间: 2013
• 期刊: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
• 作者: Astrinaki M.

TRANSCRIPTION OF MULTI-GENRE MEDIA ARCHIVES USING OUT-OF-DOMAIN DATA

• DOI: 10.1109/slt.2012.6424244
• 发表时间: 2012-01-01
• 期刊: 2012 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2012)
• 作者: Bell, P. J.;Gales, M. J. F.;Woodland, P. C.
• 通讯作者: Woodland, P. C.

A system for automatic alignment of broadcast media captions using weighted finite-state transducers

• DOI: 10.1109/asru.2015.7404861
• 发表时间: 2015-12
• 期刊: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)
• 作者: P. Bell;S. Renals

Multi-level adaptive networks in tandem and hybrid ASR systems

• DOI: 10.1109/icassp.2013.6639014
• 发表时间: 2013-05
• 期刊: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
• 作者: P. Bell;P. Swietojanski;S. Renals