Lam, MWY;
Wang, J;
Su, D;
Yu, D;
(2021)
Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks.
In:
Proceedings of the 2021 IEEE Spoken Language Technology Workshop (SLT).
(pp. pp. 801-808).
IEEE
Preview |
Text
2101.05014.pdf - Accepted Version Download (934kB) | Preview |
Abstract
Recent research on the time-domain audio separation networks (TasNets) has brought great success to speech separation. Nevertheless, conventional TasNets struggle to satisfy the memory and latency constraints in industrial applications. In this regard, we design a low-cost high-performance architecture, namely, globally attentive locally recurrent (GALR) network. Alike the dual-path RNN (DPRNN), we first split a feature sequence into 2D segments and then process the sequence along both the intra- and inter-segment dimensions. Our main innovation lies in that, on top of features recurrently processed along the inter-segment dimensions, GALR applies a self-attention mechanism to the sequence along the inter-segment dimension, which aggregates context-aware information and also enables parallelization. Our experiments suggest that GALR is a notably more effective network than the prior work. On one hand, with only 1.5M parameters, it has achieved comparable separation performance at a much lower cost with 36.1% less runtime memory and 49.4% fewer computational operations, relative to the DPRNN. On the other hand, in a comparable model size with DPRNN, GALR has consistently outperformed DPRNN in three datasets, in particular, with a substantial margin of 2.4dB absolute improvement of SI-SNRi in the benchmark WSJ0-2mix task.
| Type: | Proceedings paper |
|---|---|
| Title: | Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks |
| Event: | 2021 IEEE Spoken Language Technology Workshop (SLT) |
| Location: | Shenzhen, China |
| Dates: | 19th-22nd Jan 2021 |
| ISBN-13: | 9781728170664 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/SLT48900.2021.9383464 |
| Publisher version: | https://doi.org/10.1109/SLT48900.2021.9383464 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. |
| Keywords: | speech separation, TasNet, low-cost, multi-head attention |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10154105 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
