Design and Implementation of a Low-Latency, Lightweight, High-Performance Voice Interface Front-End

Heeb T, Stanford-Jason A, Leidi T. Design and Implementation of a Low-Latency, Lightweight, High-Performance Voice Interface Front-End. In: AES Convention 140. Audio Engineering Society; 2016. Paper 264. Available from: https://aes.org/publications/elibrary-page/?id=18168

@inproceedings{Heeb2016_18168,
  author = {Heeb, Thierry and Stanford-Jason, Andrew and Leidi, Tiziano},
  title = {{Design and Implementation of a Low-Latency, Lightweight, High-Performance Voice Interface Front-End}},
  booktitle = {AES Convention 140},
  note = {Paper 264},
  year = {2016},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=18168}
}

TY  - CPAPER
TI  - Design and Implementation of a Low-Latency, Lightweight, High-Performance Voice Interface Front-End
AU  - Heeb, Thierry
AU  - Stanford-Jason, Andrew
AU  - Leidi, Tiziano
T2  - AES Convention 140
M1  - Paper 264
PY  - 2016
DA  - 2016/05/06
UR  - https://aes.org/publications/elibrary-page/?id=18168
PB  - Audio Engineering Society
LA  - en
AB  - 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.
ER  -