An Acoustic Front-End to Speech Recognition in a Vehicle

Every M, Li X. An Acoustic Front-End to Speech Recognition in a Vehicle. In: AES Conference: AES 2022 International Automotive Audio Conference. Audio Engineering Society; 2022. Paper 3. Available from: https://aes.org/publications/elibrary-page/?id=21804

@inproceedings{Every2022_21804,
  author = {Every, Mark and Li, Xueman},
  title = {{An Acoustic Front-End to Speech Recognition in a Vehicle}},
  booktitle = {AES Conference: AES 2022 International Automotive Audio Conference},
  note = {Paper 3},
  year = {2022},
  month = jun,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=21804}
}

TY  - CPAPER
TI  - An Acoustic Front-End to Speech Recognition in a Vehicle
AU  - Every, Mark
AU  - Li, Xueman
T2  - AES Conference: AES 2022 International Automotive Audio Conference
M1  - Paper 3
PY  - 2022
DA  - 2022/06/06
UR  - https://aes.org/publications/elibrary-page/?id=21804
PB  - Audio Engineering Society
LA  - en
AB  - The acceptance of speech as a primary user-interface in vehicles depends on how well speech recognition can overcome challenging conditions including high levels of noise, echo and competing speech, in which accuracy is known to degrade. To mitigate this, an acoustic front-end using the QNX Acoustics for Voice software library preprocesses multichannel microphone data from the vehicle and provides a cleaned signal to the recognizer. We demonstrate how three components of the front-end: beamforming, acoustic echo cancellation and zone interference cancellation, lead to significant improvements in word error rates.
ER  -