mlsanityData to 13 Oct 2026

Individualized Conditioning and Negative Distances for Speaker Separation

arXiv 2210.06368 ↗First posted 12 Oct 2022cs.SD cs.AI eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Speaker separation aims to extract multiple voices from a mixed signal. In this paper, we propose two speaker-aware designs to improve the existing speaker separation solutions. The first model is a speaker conditioning network that integrates speech samples to generate individualized speaker conditions, which then provide informed guidance for a separation module to produce well-separated outputs. The second design aims to reduce non-target voices in the separated speech. To this end, we propose negative distances to penalize the appearance of any non-target voice in the channel outputs, and positive distances to drive the separated voices closer to the clean targets. We explore two different setups, weighted-sum and triplet-like, to integrate these two distances to form a combined auxiliary loss for the separation networks. Experiments conducted on LibriMix demonstrate the effectiveness of our proposed models.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 12 Oct 2022.

Builds on

27 of 38 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,838
  3. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,306
  4. 2020Self-supervised Learning: Generative or Contrastivecited by 694
  5. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 402
  6. 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 337
  7. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 213
  8. 2016Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separationcited by 190
  9. 2020TERA: Self-Supervised Learning of Transformer Encoder Representation for Speechcited by 187
  10. 2020Attention is All You Need in Speech Separationcited by 184
  11. 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 182
  12. 2020LibriMix: An Open-Source Dataset for Generalizable Speech Separationcited by 155
15 more
  1. 2020Multi-task self-supervised learning for Robust Speech Recognitioncited by 127
  2. 2017TasNet: time-domain audio separation network for real-time, single-channel speech separationcited by 115
  3. 2017Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networkscited by 97
  4. 2019Learning Problem-agnostic Speech Representations from Multiple Self-supervised Taskscited by 87
  5. 2020Wavesplit: End-to-End Speech Separation by Speaker Clusteringcited by 74
  6. 2020Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separationcited by 67
  7. 2020Voice Separation with an Unknown Number of Multiple Speakerscited by 46
  8. 2016Single-Channel Multi-Speaker Separation using Deep Clusteringcited by 45
  9. 2016Deep attractor network for single-microphone speaker separationcited by 26
  10. 2020Improved RawNet with Feature Map Scaling for Text-independent Speaker Verification using Raw Waveformscited by 12
  11. 2020Speaker-Conditional Chain Model for Speech Separation and Extractioncited by 4
  12. 2021On permutation invariant training for speech source separationcited by 4
  13. 2021Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separationcited by 4
  14. 2019Dilated FCN: Listening Longer to Hear Bettercited by 3
  15. 2020Speech Separation Based on Multi-Stage Elaborated Dual-Path Deep BiLSTM with Auxiliary Identity Losscited by 3

Built on by

Not cited yet.