Speaker-aware target speaker enhancement by jointly learning with speaker embedding extraction

X Ji, M Yu, C Zhang, D Su, T Yu… - ICASSP 2020-2020 …, 2020 - ieeexplore.ieee.org
X Ji, M Yu, C Zhang, D Su, T Yu, X Liu, D Yu
ICASSP 2020-2020 IEEE International Conference on Acoustics …, 2020ieeexplore.ieee.org
Deep learning based speech separation approaches have received great interest, among
which the recent speaker-aware speech enhancement methods are promising for solving
difficulties such as arbitrary source permutation and unknown number of sources. In this
paper, we propose a novel training framework which jointly learns the speaker-conditioned
target speaker extraction model and its associated speaker embedding model. The resulting
unified model directly learns the appropriate speaker embedding for improved target speech …
Deep learning based speech separation approaches have received great interest, among which the recent speaker-aware speech enhancement methods are promising for solving difficulties such as arbitrary source permutation and unknown number of sources. In this paper, we propose a novel training framework which jointly learns the speaker-conditioned target speaker extraction model and its associated speaker embedding model. The resulting unified model directly learns the appropriate speaker embedding for improved target speech enhancement. We demonstrate, on our large simulated noisy and far-field evaluation sets of overlapped speech signals, that our proposed approach significantly improves the speech enhancement performance compared to the baseline speaker-aware speech enhancement models.
ieeexplore.ieee.org
Showing the best result for this search. See all results