Speech Separation based on Contrastive Learning and Deep Modularization

• URL: http://arxiv.org/abs/2305.10652v4
• Date: Wed, 09 Oct 2024 13:06:48 GMT
• Title: Speech Separation based on Contrastive Learning and Deep Modularization
• Authors: Peter Ochieng,
• Abstract summary: In this paper, we use contrastive learning to establish the representations of frames then use the learned representations in the downstream deep modularization task. Based on this, we implement a self-supervised learning to learn to minimize the distance between frames belonging to a given speaker. The learned representations are used in a downstream deep modularization task to cluster frames based on speaker identity.
• Score: 3.2634122554914002
• License:
• Abstract: The current monaural state of the art tools for speech separation relies on supervised learning. This means that they must deal with permutation problem, they are impacted by the mismatch on the number of speakers used in training and inference. Moreover, their performance heavily relies on the presence of high-quality labelled data. These problems can be effectively addressed by employing a fully unsupervised technique for speech separation. In this paper, we use contrastive learning to establish the representations of frames then use the learned representations in the downstream deep modularization task. Concretely, we demonstrate experimentally that in speech separation, different frames of a speaker can be viewed as augmentations of a given hidden standard frame of that speaker. The frames of a speaker contain enough prosodic information overlap which is key in speech separation. Based on this, we implement a self-supervised learning to learn to minimize the distance between frames belonging to a given speaker. The learned representations are used in a downstream deep modularization task to cluster frames based on speaker identity. Evaluation of the developed technique on WSJ0-2mix and WSJ0-3mix shows that the technique attains SI-SNRi and SDRi of 20.8 and 21.0 respectively in WSJ0-2mix. In WSJ0-3mix, it attains SI-SNRi and SDRi of 20.7 and 20.7 respectively in WSJ0-2mix. Its greatest strength being that as the number of speakers increase, its performance does not degrade significantly.

Related papers

• Online speaker diarization of meetings guided by speech separation [0.0]
  Overlapped speech is notoriously problematic for speaker diarization systems. We introduce a new speech separation-guided diarization scheme suitable for the online speaker diarization of long meeting recordings.
  arXiv  Detail & Related papers  (2024-01-30T09:09:22Z)
• Disentangling Voice and Content with Self-Supervision for Speaker Recognition [57.446013973449645]
  This paper proposes a disentanglement framework that simultaneously models speaker traits and content variability in speech. It is validated with experiments conducted on the VoxCeleb and SITW datasets with 9.56% and 8.24% average reductions in EER and minDCF.
  arXiv  Detail & Related papers  (2023-10-02T12:02:07Z)
• Getting More for Less: Using Weak Labels and AV-Mixup for Robust Audio-Visual Speaker Verification [0.4681661603096334]
  We show that an auxiliary task with even weak labels can increase the quality of the learned speaker representation. We also extend the Generalized End-to-End Loss (GE2E) to multimodal inputs and demonstrate that it can achieve competitive performance in an audio-visual space. Our network achieves state of the art performance for speaker verification, reporting 0.244%, 0.252%, 0.441% Equal Error Rate (EER) on the VoxCeleb1-O/E/H test sets.
  arXiv  Detail & Related papers  (2023-09-13T17:45:41Z)
• Multi-Dimensional and Multi-Scale Modeling for Speech Separation Optimized by Discriminative Learning [9.84949849886926]
  Intra-SE-Conformer and Inter-Transformer (ISCIT) for speech separation. New network SE-Conformer can model audio sequences in multiple dimensions and scales.
  arXiv  Detail & Related papers  (2023-03-07T08:53:20Z)
• SLICER: Learning universal audio representations using low-resource self-supervised pre-training [53.06337011259031]
  We present a new Self-Supervised Learning approach to pre-train encoders on unlabeled audio data. Our primary aim is to learn audio representations that can generalize across a large variety of speech and non-speech tasks.
  arXiv  Detail & Related papers  (2022-11-02T23:45:33Z)
• Attention-based conditioning methods using variable frame rate for style-robust speaker verification [21.607777746331998]
  We propose an approach to extract speaker embeddings robust to speaking style variations in text-independent speaker verification. An entropy-based variable frame rate vector is proposed as an external conditioning vector for the self-attention layer.
  arXiv  Detail & Related papers  (2022-06-28T01:14:09Z)
• Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation [59.41186714127256]
  Dysarthric speech reconstruction (DSR) aims to improve the quality of dysarthric speech. Speaker encoder (SE) optimized for speaker verification has been explored to control the speaker identity. We propose a novel multi-task learning strategy, i.e., adversarial speaker adaptation (ASA)
  arXiv  Detail & Related papers  (2022-02-18T08:59:36Z)
• Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition [52.71604809100364]
  We propose wav2vec-Switch, a method to encode noise robustness into contextualized representations of speech. Specifically, we feed original-noisy speech pairs simultaneously into the wav2vec 2.0 network. In addition to the existing contrastive learning task, we switch the quantized representations of the original and noisy speech as additional prediction targets.
  arXiv  Detail & Related papers  (2021-10-11T00:08:48Z)
• PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction [90.55375210094995]
  Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. We propose an end-to-end deep learning framework, dubbed PL-EESR, for robust speaker representation extraction.
  arXiv  Detail & Related papers  (2021-10-03T07:05:29Z)
• VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion [54.29557210925752]
  One-shot voice conversion can be effectively achieved by speech representation disentanglement. We employ vector quantization (VQ) for content encoding and introduce mutual information (MI) as the correlation metric during training. Experimental results reflect the superiority of the proposed method in learning effective disentangled speech representations.
  arXiv  Detail & Related papers  (2021-06-18T13:50:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.