Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

FurcaNeXt: End-to-end monaural speech separation with dynamic gated dilated temporal convolutional networks (1902.04891v6)

Published 12 Feb 2019 in cs.SD and eess.AS

Abstract: Deep dilated temporal convolutional networks (TCN) have been proved to be very effective in sequence modeling. In this paper we propose several improvements of TCN for end-to-end approach to monaural speech separation, which consists of 1) multi-scale dynamic weighted gated dilated convolutional pyramids network (FurcaPy), 2) gated TCN with intra-parallel convolutional components (FurcaPa), 3) weight-shared multi-scale gated TCN (FurcaSh), 4) dilated TCN with gated difference-convolutional component (FurcaSu), that all these networks take the mixed utterance of two speakers and maps it to two separated utterances, where each utterance contains only one speaker's voice. For the objective, we propose to train the network by directly optimizing utterance level signal-to-distortion ratio (SDR) in a permutation invariant training (PIT) style. Our experiments on the the public WSJ0-2mix data corpus results in 18.4dB SDR improvement, which shows our proposed networks can leads to performance improvement on the speaker separation task.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Liwen Zhang (34 papers)
  2. Ziqiang Shi (27 papers)
  3. Jiqing Han (26 papers)
  4. Anyan Shi (2 papers)
  5. Ding Ma (26 papers)
Citations (91)

Summary

We haven't generated a summary for this paper yet.