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
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

SpEx+: A Complete Time Domain Speaker Extraction Network (2005.04686v2)

Published 10 May 2020 in eess.AS and cs.SD

Abstract: Speaker extraction aims to extract the target speech signal from a multi-talker environment given a target speaker's reference speech. We recently proposed a time-domain solution, SpEx, that avoids the phase estimation in frequency-domain approaches. Unfortunately, SpEx is not fully a time-domain solution since it performs time-domain speech encoding for speaker extraction, while taking frequency-domain speaker embedding as the reference. The size of the analysis window for time-domain and the size for frequency-domain input are also different. Such mismatch has an adverse effect on the system performance. To eliminate such mismatch, we propose a complete time-domain speaker extraction solution, that is called SpEx+. Specifically, we tie the weights of two identical speech encoder networks, one for the encoder-extractor-decoder pipeline, another as part of the speaker encoder. Experiments show that the SpEx+ achieves 0.8dB and 2.1dB SDR improvement over the state-of-the-art SpEx baseline, under different and same gender conditions on WSJ0-2mix-extr database respectively.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Meng Ge (29 papers)
  2. Chenglin Xu (14 papers)
  3. Longbiao Wang (46 papers)
  4. Eng Siong Chng (112 papers)
  5. Jianwu Dang (41 papers)
  6. Haizhou Li (286 papers)
Citations (131)

Summary

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