Abstract | ||
---|---|---|
We present a novel source separation model to decompose asingle-channel speech signal into two speech segments belonging to two different speakers. The proposed model is a neural network based on residual blocks, and uses learnt speaker embeddings created from additional clean context recordings of the two speakers as input to assist in attributing the different time-frequency bins to the two speakers. In experiments, we show that the proposed model yields good performance in the source separation task, and outperforms the state-of-the-art baselines. Specifically, separating speech from the challenging VoxCeleb dataset, the proposed model yields 4.79dB signal-to-distortion ratio, 8.44dB signal-to-artifacts ratio and 7.11dB signal-to-interference ratio. |
Year | Venue | DocType |
---|---|---|
2019 | CoRR | Journal |
Volume | Citations | PageRank |
abs/1906.09997 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shuo Liu | 1 | 33 | 16.80 |
Gil Keren | 2 | 4 | 1.76 |
Björn Schuller | 3 | 6749 | 463.50 |