Title | ||
---|---|---|
DIRECTIONAL ASR: A NEW PARADIGM FOR E2E MULTI-SPEAKER SPEECH RECOGNITION WITH SOURCE LOCALIZATION |
Abstract | ||
---|---|---|
This paper proposes a new paradigm for handling far-field multi-speaker data in an end-to-end (E2E) neural network manner, called directional automatic speech recognition (D-ASR), which explicitly models source speaker locations. In D-ASR, the azimuth angle of the sources with respect to the microphone array is defined as a latent variable. This angle controls the quality of separation, which in turn determines the ASR performance. All three functionalities of D-ASR: localization, separation, and recognition are connected as a single differentiable neural network and trained solely based on ASR error minimization objectives. The advantages of D-ASR over existing methods are threefold: (1) it provides explicit speaker locations, (2) it improves the explainability factor, and (3) it achieves better ASR performance as the process is more streamlined. In addition, D-ASR does not require explicit direction of arrival (DOA) supervision like existing data-driven localization models, which makes it more appropriate for realistic data. For the case of two source mixtures, D-ASR achieves an average DOA prediction error of less than three degrees. It also outperforms a strong far-field multi-speaker end-to-end system in both separation quality and ASR performance. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICASSP39728.2021.9414243 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
source localization, source separation, end-to-end speech recognition | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
S. Aswin Shanmugam | 1 | 7 | 4.21 |
Chao Weng | 2 | 113 | 19.75 |
Shinji Watanabe | 3 | 1158 | 139.38 |
Meng Yu | 4 | 524 | 66.52 |
Yong Xu | 5 | 276 | 24.71 |
Shi-Xiong Zhang | 6 | 18 | 6.75 |
Dong Yu | 7 | 6264 | 475.73 |