Audioscenic Adaptive Audio Beamforming Technology for Automotive Applications

适用于汽车应用的 Audioscenic 自适应音频波束形成技术

• 批准号: 10047916
• 金额: $ 83.94万
• 依托单位: SOTON AUDIO LABS LIMITED
• 依托单位国家: 英国
• 项目类别: Investment Accelerator
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=10047916
• 关键词: Audioscenic; Adaptive; Audio; Beamforming; Technology

The project will deliver a greatly improved automotive audio experience for drivers and passengers in commercial or private vehicles. Automotive cabins are a difficult acoustic environment; they are relatively small and have hard reflective surfaces, such as windows, close to the listener's ears. The Audioscenic technology uses patented adaptive audio beam forming technology to overcome these issues to deliver a listening experience as good as anything possible in your living room. The Audioscenic technology will deliver this enhanced listening experience without the need for any complicated user set-up or factory tuning as the Audioscenic technology automatically adapts in real-time to the listener's position, instantaneously optimising the audio for any small movements of the listener's head.The project will focus on adapting the Audioscenic core technology, already deployed for desktop audio applications, to automotive applications. This will require the development of a new version of the company's AI powered listener tracking technology, to locate the listener's ears and allow for head movements. It will also require the development of new versions of the company's adaptive beam forming acoustic algorithms to allow for the speaker locations in the vehicle, which will be very different from the locations in the current desktop products.The automotive application of Audioscenic's technology will be innovative and different from any other technologies currently on the market. The technology will allow the driver and each individual passenger in the vehicle to listen to different audio. So, for example, the driver can listen to directions from the Sat Nav at the same time as a passenger in the front listens to a telephone conference call and a passenger in one of the rear seats watches a movie and listens to the soundtrack. Furthermore, the audio will be 3D and can sound as good as the best cinema surround sound or living room high end home audio system. So the driver's directions from the Sat Nav will tell them to turn left, with the instructions appearing to come from the direction of the turn. The passenger listening to a telephone conference call can hear the different participants in the call as if they were spaced around them in a meeting room and the passenger listening to the movie soundtrack will hear the audio they would hear sitting in a cinema with a full surround sound system with speakers located all around the auditorium.

该项目将为商用或私家车的司机和乘客提供大大改善的汽车音频体验。汽车舱室是一个困难的声学环境；它们相对较小，并且有坚硬的反射表面，例如靠近听者耳朵的窗户。Audioscenic技术采用专利的自适应音频波束形成技术来克服这些问题，在您的客厅中提供尽可能好的聆听体验。Audioscenic技术将提供这种增强的聆听体验，而无需任何复杂的用户设置或工厂调整，因为Audioscenic技术会自动实时适应听众的位置，即时优化听众头部的任何微小运动的音频。该项目将专注于将Audioscenic核心技术应用于汽车应用，该技术已经部署在桌面音频应用中。这将需要开发新版本的人工智能听者跟踪技术，以定位听者的耳朵并允许头部运动。它还需要开发公司自适应波束形成声学算法的新版本，以允许车辆中的扬声器位置，这将与当前桌面产品中的位置有很大不同。Audioscenic技术的汽车应用将是创新的，与目前市场上的任何其他技术都不同。这项技术将允许司机和车内的每位乘客收听不同的音频。例如，驾驶员可以在前排乘客听电话会议、后排乘客看电影并听电影原声带的同时，收听卫星导航系统的指示。此外，音频将是3D的，听起来可以像最好的影院环绕声或客厅高端家庭音响系统一样好。因此，驾驶员从卫星导航系统得到的指示会告诉他们左转，指示似乎来自转弯的方向。听电话会议的乘客可以听到电话中不同参与者的声音，就好像他们在会议室里被隔开一样；听电影原声的乘客会听到他们坐在影院里听到的声音，影院里有环绕立体声系统，扬声器遍布整个礼堂。