Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models

• URL: http://arxiv.org/abs/2506.10855v1
• Date: Thu, 12 Jun 2025 16:16:38 GMT
• Title: Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models
• Authors: Michele Gubian, Ioana Krehan, Oli Liu, James Kirby, Sharon Goldwater,
• Abstract summary: We show how wav2vec2 models trained on four different languages encode both language-matched and non-matched speech.<n>Our findings suggest that the structure of representations learned by wav2vec2 is largely independent of the speech material used during pretraining.
• Score: 5.874344393486844
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Analyses of self-supervised speech models have begun to reveal where and how they represent different types of information. However, almost all analyses have focused on English. Here, we examine how wav2vec2 models trained on four different languages encode both language-matched and non-matched speech. We use probing classifiers and geometric analyses to examine how phones, lexical tones, and speaker information are represented. We show that for all pretraining and test languages, the subspaces encoding phones, tones, and speakers are largely orthogonal, and that layerwise patterns of probing accuracy are similar, with a relatively small advantage for matched-language phone and tone (but not speaker) probes in the later layers. Our findings suggest that the structure of representations learned by wav2vec2 is largely independent of the speech material used during pretraining.

Related papers

• Teach me with a Whisper: Enhancing Large Language Models for Analyzing Spoken Transcripts using Speech Embeddings [8.660203441911554]
  We propose a methodology for training language models leveraging spoken language audio data. This leads to an improved language model for analyzing spoken transcripts while avoiding an audio processing overhead at test time. In our experiments, the student model achieves consistent improvement over traditional language models on tasks analyzing spoken transcripts.
  arXiv  Detail & Related papers  (2023-11-13T01:53:12Z)
• 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)
• Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features [35.31998003091635]
  We introduce a new approach to explain speech classification models. We generate easy-to-interpret explanations via input perturbation on two information levels. We validate our approach by explaining two state-of-the-art SLU models on two speech classification tasks in English and Italian.
  arXiv  Detail & Related papers  (2023-09-14T14:12:34Z)
• AudioPaLM: A Large Language Model That Can Speak and Listen [79.44757696533709]
  We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models. It can process and generate text and speech with applications including speech recognition and speech-to-speech translation.
  arXiv  Detail & Related papers  (2023-06-22T14:37:54Z)
• Learning Cross-lingual Visual Speech Representations [108.68531445641769]
  Cross-lingual self-supervised visual representation learning has been a growing research topic in the last few years. We use the recently-proposed Raw Audio-Visual Speechs (RAVEn) framework to pre-train an audio-visual model with unlabelled data. Our experiments show that: (1) multi-lingual models with more data outperform monolingual ones, but, when keeping the amount of data fixed, monolingual models tend to reach better performance.
  arXiv  Detail & Related papers  (2023-03-14T17:05:08Z)
• Unified Speech-Text Pre-training for Speech Translation and Recognition [113.31415771943162]
  We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality learning. It achieves between 1.7 and 2.3 BLEU improvement above the state of the art on the MuST-C speech translation dataset.
  arXiv  Detail & Related papers  (2022-04-11T20:59:51Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• Leveraging Pre-trained Language Model for Speech Sentiment Analysis [58.78839114092951]
  We explore the use of pre-trained language models to learn sentiment information of written texts for speech sentiment analysis. We propose a pseudo label-based semi-supervised training strategy using a language model on an end-to-end speech sentiment approach.
  arXiv  Detail & Related papers  (2021-06-11T20:15:21Z)
• 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)
• CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning [11.552745999302905]
  More than half of the 7,000 languages in the world are in imminent danger of going extinct. It is relatively easy to obtain textual translations corresponding to speech. We construct a convolutional neural network audio encoder capable of extracting linguistic representations from speech.
  arXiv  Detail & Related papers  (2020-06-04T12:21:48Z)
• Cross-lingual Multispeaker Text-to-Speech under Limited-Data Scenario [10.779568857641928]
  This paper presents an extension on Tacotron2 to achieve bilingual multispeaker speech synthesis. We achieve cross-lingual synthesis, including code-switching cases, between English and Mandarin for monolingual speakers.
  arXiv  Detail & Related papers  (2020-05-21T03:03:34Z)

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.