What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis

• URL: http://arxiv.org/abs/2401.17632v1
• Date: Wed, 31 Jan 2024 07:23:22 GMT
• Title: What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis
• Authors: Takanori Ashihara, Marc Delcroix, Takafumi Moriya, Kohei Matsuura, Taichi Asami, Yusuke Ijima
• Abstract summary: Self-supervised learning (SSL) has attracted increased attention for learning meaningful speech representations. Speaker SSL models adopt utterance-level training objectives primarily for speaker representation.
• Score: 44.93152068353389
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised learning (SSL) has attracted increased attention for learning meaningful speech representations. Speech SSL models, such as WavLM, employ masked prediction training to encode general-purpose representations. In contrast, speaker SSL models, exemplified by DINO-based models, adopt utterance-level training objectives primarily for speaker representation. Understanding how these models represent information is essential for refining model efficiency and effectiveness. Unlike the various analyses of speech SSL, there has been limited investigation into what information speaker SSL captures and how its representation differs from speech SSL or other fully-supervised speaker models. This paper addresses these fundamental questions. We explore the capacity to capture various speech properties by applying SUPERB evaluation probing tasks to speech and speaker SSL models. We also examine which layers are predominantly utilized for each task to identify differences in how speech is represented. Furthermore, we conduct direct comparisons to measure the similarities between layers within and across models. Our analysis unveils that 1) the capacity to represent content information is somewhat unrelated to enhanced speaker representation, 2) specific layers of speech SSL models would be partly specialized in capturing linguistic information, and 3) speaker SSL models tend to disregard linguistic information but exhibit more sophisticated speaker representation.

Related papers

• Do self-supervised speech and language models extract similar representations as human brain? [2.390915090736061]
  Speech and language models trained through self-supervised learning (SSL) demonstrate strong alignment with brain activity during speech and language perception. We evaluate the brain prediction performance of two representative SSL models, Wav2Vec2.0 and GPT-2.
  arXiv  Detail & Related papers  (2023-10-07T01:39:56Z)
• SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge? [39.62926623310278]
  Self-supervised learning (SSL) for speech representation has been successfully applied in various downstream tasks. In this paper, we aim to clarify if speech SSL techniques can well capture linguistic knowledge.
  arXiv  Detail & Related papers  (2023-06-14T09:04:29Z)
• The Ability of Self-Supervised Speech Models for Audio Representations [53.19715501273934]
  Self-supervised learning (SSL) speech models have achieved unprecedented success in speech representation learning. We conduct extensive experiments on abundant speech and non-speech audio datasets to evaluate the representation ability of state-of-the-art SSL speech models. Results show that SSL speech models could extract meaningful features of a wide range of non-speech audio, while they may also fail on certain types of datasets.
  arXiv  Detail & Related papers  (2022-09-26T15:21:06Z)
• Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning [13.391307807956673]
  We propose a novel automatic pronunciation assessment method based on self-supervised learning (SSL) models. First, the proposed method fine-tunes the pre-trained SSL models with connectionist temporal classification to adapt the English pronunciation of English-as-a-second-language learners. We show that the proposed SSL model-based methods outperform the baselines, in terms of the Pearson correlation coefficient, on datasets of Korean ESL learner children and Speechocean762.
  arXiv  Detail & Related papers  (2022-04-08T06:13:55Z)
• 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)
• SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding [61.02342238771685]
  Spoken language understanding requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. Various pre-training methods have been proposed to learn rich representations from large-scale unannotated speech and text. We propose a novel semi-supervised learning framework, SPLAT, to jointly pre-train the speech and language modules.
  arXiv  Detail & Related papers  (2020-10-05T19:29:49Z)
• Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation [51.37980448183019]
  We propose Audio ALBERT, a lite version of the self-supervised speech representation model. We show that Audio ALBERT is capable of achieving competitive performance with those huge models in the downstream tasks. In probing experiments, we find that the latent representations encode richer information of both phoneme and speaker than that of the last layer.
  arXiv  Detail & Related papers  (2020-05-18T10:42:44Z)

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.