English

An enhanced Conv-TasNet model for speech separation using a speaker distance-based loss function

Audio and Speech Processing 2022-06-20 v3

Abstract

This work addresses the problem of speech separation in the Spanish Language using pre-trained deep learning models. As with many speech processing tasks, large databases in other languages different from English are scarce. Therefore this work explores different training strategies using the Conv-TasNet model as a benchmark. A scale-invariant signal distortion ratio (SI-SDR) metric value of 9.9 dB was achieved for the best training strategy. Then, experimentally, we identified an inverse relationship between the speakers' similarity and the model's performance, so an improved ConvTasNet architecture was proposed. The enhanced Conv-TasNet model uses pre-trained speech embeddings to add a between-speakers cosine similarity term in the cost function, yielding an SI-SDR of 10.6 dB. Lastly, final experiments regarding real-time deployment show some drawbacks in the speakers' channel synchronization due to the need to process small speech segments where only one of the speakers appears.

Keywords

Cite

@article{arxiv.2205.13657,
  title  = {An enhanced Conv-TasNet model for speech separation using a speaker distance-based loss function},
  author = {Jose A. Arango-Sánchez and Julián D. Arias-Londoño},
  journal= {arXiv preprint arXiv:2205.13657},
  year   = {2022}
}

Comments

https://github.com/DW-Speech-Separation/train-test-ConvTasNet

R2 v1 2026-06-24T11:30:15.978Z