Multi-task Based Sound Localization Model

Song T, Qu T, Chen J. Multi-task Based Sound Localization Model. In: AES Convention 148. Audio Engineering Society; 2020. Paper 10366. Available from: https://aes.org/publications/elibrary-page/?id=20783

@inproceedings{Song2020_20783,
  author = {Song, Tao and Qu, Tianshu and Chen, Jing},
  title = {{Multi-task Based Sound Localization Model}},
  booktitle = {AES Convention 148},
  note = {Paper 10366},
  year = {2020},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20783}
}

TY  - CPAPER
TI  - Multi-task Based Sound Localization Model
AU  - Song, Tao
AU  - Qu, Tianshu
AU  - Chen, Jing
T2  - AES Convention 148
M1  - Paper 10366
PY  - 2020
DA  - 2020/05/06
UR  - https://aes.org/publications/elibrary-page/?id=20783
PB  - Audio Engineering Society
LA  - en
AB  - For machine hearing in complex sences (i.e. reverberation, noise), sound localization either serves as the front-end or is implicitly encoded in speech enhancing models. However, it is suggested that there may be cross-talk between identification and localization streams in auditory system. Based on this idea, a multi-task based sound localization method is proposed in this study. The proposed model takes waveform as input, and simutaneously estimates the azimuth of sound source and the time-frequency (T-F) masks. Localization experiments were performed using binaural simulation in reverberant environment and the results show that comparing to single-task sound localization method, the presence of speech enhancement task can improve the localization performance.
ER  -