Smart voice interfaces are the enabler of a new generation of consumer products such as network connected, voice enabled personal assistants. These are based on distributed architectures where voice is captured and pre-processed locally before being sent to remote servers for semantic analysis and response generation. A key element to achieve lowest cost and the best natural speech user experience is to keep latency to a minimum. This eBrief presents a lightweight, high-performance voice interface front-end software framework capable of handling multiple PDM microphones and integrating PDM to PCM conversion, high-resolution inter-channel delay, decimation, signal correction, and optional output data framing. The software forms a complete smart voice interface front-end running on the XMOS xCORE-200 architecture and achieving very low latency.
https://www.aes.org/e-lib/browse.cfm?elib=18168
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.
Learn more about the AES E-Library
The Engineering Briefs at this Convention were selected on the basis of a submitted synopsis, ensuring that they are of interest to AES members, and are not overly commercial. These briefs have been reproduced from the authors' advance manuscripts, without editing, corrections, or consideration by the Review Board. The AES takes no responsibility for their contents. Paper copies are not available, but any member can freely access these briefs. Members are encouraged to provide comments that enhance their usefulness.
Start a discussion about this paper!
