Source separation and noise reduction for automatic speech recognition in dynamic acoustic scenarios

动态声学场景中自动语音识别的源分离和降噪

• 批准号: 316471544
• 负责人: Professor Dr.-Ing. Reinhold Häb-Umbach
• 金额: --
• 依托单位: Institut für Elektrotechnik und Informationstechnik
• 依托单位国家: 德国
• 项目类别: Research Grants (Transfer Project)
• 财政年份: 2016
• 资助国家: 德国
• 起止时间: 2015-12-31 至 2020-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/316471544?language=en
• 关键词: Source; separation; noise; reduction; automatic

The goal of the project is the development of an automatic speech recognition system to be used for hands-free voice control in a smart home environment. Starting with the multi-channel blind source separation and noise reduction techniques developed in the DFG-funded preceding project, these algorithms will be further developed and optimized with respect to latency and realizability on resource-constrained embedded hardware. The prototyp to be developed shall perform recognition in real-time with low latency and achieve superior recognition rates in acoustic environments typical of smart home applications compared to an existing speech recognition system available at the industrial partner.As an alternative to the above parametric source separation and speech enhancement algorithms, we will also research and develop neural network based solutions. We will carry out a thorough comparison between the two approaches with respect to enhancement/recogntion performance, latency, computational and memory requirements and robustness towards varying acoustic environmental conditions.

该项目的目标是开发自动语音识别系统，用于智能家居环境中的免提语音控制。从 DFG 资助的前期项目中开发的多通道盲源分离和降噪技术开始，这些算法将在资源受限的嵌入式硬件上的延迟和可实现性方面得到进一步开发和优化。与工业合作伙伴现有的语音识别系统相比，要开发的原型应以低延迟进行实时识别，并在智能家居应用典型的声学环境中实现卓越的识别率。作为上述参数源分离的替代方案和语音增强算法，我们还将研究和开发基于神经网络的解决方案。我们将在增强/识别性能、延迟、计算和内存要求以及对不同声学环境条件的鲁棒性方面对两种方法进行彻底的比较。

项目成果

A Study on Online Source Extraction in the Presence of Changing Speaker Positions

• DOI: 10.1007/978-3-030-31372-2_17
• 发表时间: 2019-10
• 作者: Jens Heitkaemper;T. Fehér;M. Freitag;Reinhold Häb-Umbach

DEMYSTIFYING TASNET: A DISSECTING APPROACH

• DOI: 10.1109/icassp40776.2020.9052981
• 发表时间: 2020-01-01
• 期刊: 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING
• 作者: Heitkaemper, Jens;Jakobeit, Darius;Haeb-Umbach, Reinhold
• 通讯作者: Haeb-Umbach, Reinhold