TY - GEN
T1 - A sound engineering approach to near end listening enhancement
AU - Chermaz, Carol
AU - King, Simon
N1 - Funding Information:
The authors thank the organizers of the Hurricane Challenge 2.0 for performing the evaluations and Andreas Volgenandt for useful discussions on DRC. This project has received funding from the EU's H2020 research and innovation programme under the MSCA GA 67532 (the ENRICH network: www.enrich-etn.eu). Audio files are available at http://homepages.inf.ed.ac.uk/s1758351/ASEbeta.html
Publisher Copyright:
© 2020 ISCA
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/10/31
Y1 - 2020/10/31
N2 - We present the beta version of ASE (the Automatic Sound Engineer), a NELE (Near End Listening Enhancement) algorithm based on audio engineering knowledge. Generations of sound engineers have improved the intelligibility of speech against competing sounds and reverberation, while maintaining high sound quality and artistic integrity (e.g., audio track mixing in music and movies). We try to grasp the essential aspects of this expert knowledge and apply it to the more mundane context of speech playback in realistic noise. The algorithm described here was entered into the Hurricane Challenge 2.0, an evaluation of NELE algorithms. Results from those listening tests across three languages show the potential of our approach, which achieved improvements of over 7 dB EIC (Equivalent Intensity Change), corresponding to an absolute increase of 58% WAR (Word Accuracy Rate).
AB - We present the beta version of ASE (the Automatic Sound Engineer), a NELE (Near End Listening Enhancement) algorithm based on audio engineering knowledge. Generations of sound engineers have improved the intelligibility of speech against competing sounds and reverberation, while maintaining high sound quality and artistic integrity (e.g., audio track mixing in music and movies). We try to grasp the essential aspects of this expert knowledge and apply it to the more mundane context of speech playback in realistic noise. The algorithm described here was entered into the Hurricane Challenge 2.0, an evaluation of NELE algorithms. Results from those listening tests across three languages show the potential of our approach, which achieved improvements of over 7 dB EIC (Equivalent Intensity Change), corresponding to an absolute increase of 58% WAR (Word Accuracy Rate).
KW - near end listening enhancement
KW - sound engineering
KW - speech modifications
U2 - 10.21437/Interspeech.2020-2748
DO - 10.21437/Interspeech.2020-2748
M3 - Conference contribution
AN - SCOPUS:85098123358
VL - 2020-October
T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
SP - 1356
EP - 1360
BT - Proceedings of the Annual Conference of the International Speech Communication Association
T2 - 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020
Y2 - 25 October 2020 through 29 October 2020
ER -