SD-HuBERT: Sentence-Level Self-Distillation Induces Syllabic Organization in HuBERT

• URL: http://arxiv.org/abs/2310.10803v2
• Date: Tue, 16 Jan 2024 05:54:49 GMT
• Title: SD-HuBERT: Sentence-Level Self-Distillation Induces Syllabic Organization in HuBERT
• Authors: Cheol Jun Cho, Abdelrahman Mohamed, Shang-Wen Li, Alan W Black and Gopala K. Anumanchipalli
• Abstract summary: We show that a syllabic organization emerges in learning sentence-level representation of speech. We propose a new benchmark task, Spoken Speech ABX, for evaluating sentence-level representation of speech.
• Score: 49.06057768982775
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Data-driven unit discovery in self-supervised learning (SSL) of speech has embarked on a new era of spoken language processing. Yet, the discovered units often remain in phonetic space and the units beyond phonemes are largely underexplored. Here, we demonstrate that a syllabic organization emerges in learning sentence-level representation of speech. In particular, we adopt "self-distillation" objective to fine-tune the pretrained HuBERT with an aggregator token that summarizes the entire sentence. Without any supervision, the resulting model draws definite boundaries in speech, and the representations across frames exhibit salient syllabic structures. We demonstrate that this emergent structure largely corresponds to the ground truth syllables. Furthermore, we propose a new benchmark task, Spoken Speech ABX, for evaluating sentence-level representation of speech. When compared to previous models, our model outperforms in both unsupervised syllable discovery and learning sentence-level representation. Together, we demonstrate that the self-distillation of HuBERT gives rise to syllabic organization without relying on external labels or modalities, and potentially provides novel data-driven units for spoken language modeling.

Related papers

• Towards Unsupervised Speech Recognition Without Pronunciation Models [57.222729245842054]
  Most languages lack sufficient paired speech and text data to effectively train automatic speech recognition systems. We propose the removal of reliance on a phoneme lexicon to develop unsupervised ASR systems. We experimentally demonstrate that an unsupervised speech recognizer can emerge from joint speech-to-speech and text-to-text masked token-infilling.
  arXiv  Detail & Related papers  (2024-06-12T16:30:58Z)
• Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model [57.78191634042409]
  We propose Pseudo-Word HuBERT (PW-HuBERT), a framework that integrates pseudo word-level targets into the training process. Our experimental results on four spoken language understanding (SLU) benchmarks suggest the superiority of our model in capturing semantic information.
  arXiv  Detail & Related papers  (2024-02-08T16:55:21Z)
• Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study [68.88536866933038]
  Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies. Recent investigations proposed the use of discrete speech units derived from self-supervised learning representations. Applying various methods, such as de-duplication and subword modeling, can further compress the speech sequence length.
  arXiv  Detail & Related papers  (2023-09-27T17:21:13Z)
• Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration [17.94683764469626]
  We evaluate the extent to which these models' learned representations align with basic representational distinctions made by humans. We find that robust representations of both phonetic and phonemic distinctions emerge in early layers of these models' architectures. Our findings show that speech-trained HuBERT derives a low-noise and low-dimensional subspace corresponding to abstract phonological distinctions.
  arXiv  Detail & Related papers  (2023-06-09T20:07:22Z)
• Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model [21.286529902957724]
  We show that representations capturing syllabic units emerge when training a self-supervised speech model with a visually-grounded training objective. We show that our model not only outperforms a state-of-the-art syllabic segmentation method on the language it was trained on (English), but also generalizes in a zero-shot fashion to Estonian.
  arXiv  Detail & Related papers  (2023-05-19T05:19:04Z)
• Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings [4.582129557845177]
  This study tackles the unsupervised learning of semantic representations for spoken utterances. We propose WavEmbed, a sequential autoencoder that predicts hidden units from a dense representation of speech. We also propose S-HuBERT to induce meaning through knowledge distillation.
  arXiv  Detail & Related papers  (2022-10-23T21:16:09Z)
• 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)
• SLM: Learning a Discourse Language Representation with Sentence Unshuffling [53.42814722621715]
  We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation. We show that this feature of our model improves the performance of the original BERT by large margins.
  arXiv  Detail & Related papers  (2020-10-30T13:33:41Z)

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.