Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models

• URL: http://arxiv.org/abs/2406.02285v2
• Date: Mon, 16 Sep 2024 14:58:01 GMT
• Title: Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models
• Authors: Victor Miara, Theo Lepage, Reda Dehak,
• Abstract summary: Speech representations from large-scale ASR models contain valuable speaker information. We propose a framework to learn speaker representations in an SSL context by fine-tuning a pre-trained WavLM with a supervised loss. Our method achieves 0.99% EER on VoxCeleb1-O, establishing the new state-of-the-art on self-supervised SV.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems remains an ongoing challenge. Several studies have observed that speech representations from large-scale ASR models contain valuable speaker information. This work explores the limitations of fine-tuning these models for SV using an SSL contrastive objective in an end-to-end approach. Then, we propose a framework to learn speaker representations in an SSL context by fine-tuning a pre-trained WavLM with a supervised loss using pseudo-labels. Initial pseudo-labels are derived from an SSL DINO-based model and are iteratively refined by clustering the model embeddings. Our method achieves 0.99% EER on VoxCeleb1-O, establishing the new state-of-the-art on self-supervised SV. As this performance is close to our supervised baseline of 0.94% EER, this contribution is a step towards supervised performance on SV with SSL.

Related papers

• Reinforcement Learning-Guided Semi-Supervised Learning [20.599506122857328]
  We propose a novel Reinforcement Learning Guided SSL method, RLGSSL, that formulates SSL as a one-armed bandit problem. RLGSSL incorporates a carefully designed reward function that balances the use of labeled and unlabeled data to enhance generalization performance. We demonstrate the effectiveness of RLGSSL through extensive experiments on several benchmark datasets and show that our approach achieves consistent superior performance compared to state-of-the-art SSL methods.
  arXiv  Detail & Related papers  (2024-05-02T21:52:24Z)
• Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations [30.293081541301746]
  Self-supervised learning (SSL) speech models such as wav2vec and HuBERT have demonstrated state-of-the-art performance on automatic speech recognition. We argue that the problem is caused by the lack of disentangled representations and an utterance-level learning objective. Our models outperform the current best model, WavLM, on all utterance-level non-semantic tasks on the SUPERB benchmark with only 20% of labeled data.
  arXiv  Detail & Related papers  (2023-05-14T08:26:24Z)
• Improving Self-Supervised Learning by Characterizing Idealized Representations [155.1457170539049]
  We prove necessary and sufficient conditions for any task invariant to given data augmentations. For contrastive learning, our framework prescribes simple but significant improvements to previous methods. For non-contrastive learning, we use our framework to derive a simple and novel objective.
  arXiv  Detail & Related papers  (2022-09-13T18:01:03Z)
• Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition? [86.53044183309824]
  We study which factor leads to the success of self-supervised learning on speaker-related tasks. Our empirical results on the Voxceleb-1 dataset suggest that the benefit of SSL to SV task is from a combination of mask speech prediction loss, data scale, and model size.
  arXiv  Detail & Related papers  (2022-04-27T08:35:57Z)
• Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition [1.0705399532413615]
  Self-supervised learning (SSL) to learn high-level speech representations has been a popular approach to building Automatic Speech Recognition systems. We study the effect of domain, language, dataset size, and other aspects of our upstream pre-training SSL data on the final performance low-resource downstream ASR task.
  arXiv  Detail & Related papers  (2022-03-31T11:48:24Z)
• Self-Supervised Learning for speech recognition with Intermediate layer supervision [52.93758711230248]
  We propose Intermediate Layer Supervision for Self-Supervised Learning (ILS-SSL) ILS-SSL forces the model to concentrate on content information as much as possible by adding an additional SSL loss on the intermediate layers. Experiments on LibriSpeech test-other set show that our method outperforms HuBERT significantly.
  arXiv  Detail & Related papers  (2021-12-16T10:45:05Z)
• UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training [72.004873454347]
  Two methods are introduced for enhancing the unsupervised speaker information extraction. Experiment results on SUPERB benchmark show that the proposed system achieves state-of-the-art performance. We scale up training dataset to 94 thousand hours public audio data and achieve further performance improvement.
  arXiv  Detail & Related papers  (2021-10-12T05:43:30Z)
• Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning [101.28281124670647]
  Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. We propose a novel training mechanism that could effectively exploit the presence of OOD data for enhanced feature learning. Our approach substantially lifts the performance on open-set SSL and outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2021-08-12T09:14:44Z)
• On Data-Augmentation and Consistency-Based Semi-Supervised Learning [77.57285768500225]
  Recently proposed consistency-based Semi-Supervised Learning (SSL) methods have advanced the state of the art in several SSL tasks. Despite these advances, the understanding of these methods is still relatively limited.
  arXiv  Detail & Related papers  (2021-01-18T10:12:31Z)
• Semi-supervised Learning via Conditional Rotation Angle Estimation [29.8660182824314]
  We propose to couple self-supervised learning (SlfSL) with semi-supervised learning (SemSL) By implementing this idea through a simple-but-effective SlfSL approach, we create a new SemSL approach called Conditional Rotation Angle Estimation (CRAE)
  arXiv  Detail & Related papers  (2020-01-09T07:06:20Z)

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.