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

Tiny-Sepformer: A Tiny Time-Domain Transformer Network for Speech Separation (2206.13689v2)

Published 28 Jun 2022 in cs.SD and eess.AS

Abstract: Time-domain Transformer neural networks have proven their superiority in speech separation tasks. However, these models usually have a large number of network parameters, thus often encountering the problem of GPU memory explosion. In this paper, we proposed Tiny-Sepformer, a tiny version of Transformer network for speech separation. We present two techniques to reduce the model parameters and memory consumption: (1) Convolution-Attention (CA) block, spliting the vanilla Transformer to two paths, multi-head attention and 1D depthwise separable convolution, (2) parameter sharing, sharing the layer parameters within the CA block. In our experiments, Tiny-Sepformer could greatly reduce the model size, and achieves comparable separation performance with vanilla Sepformer on WSJ0-2/3Mix datasets.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Jian Luo (66 papers)
  2. Jianzong Wang (144 papers)
  3. Ning Cheng (96 papers)
  4. Edward Xiao (2 papers)
  5. Xulong Zhang (60 papers)
  6. Jing Xiao (267 papers)
Citations (11)

Summary

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