Encoding of lexical tone in self-supervised models of spoken language

• URL: http://arxiv.org/abs/2403.16865v2
• Date: Wed, 3 Apr 2024 12:59:20 GMT
• Title: Encoding of lexical tone in self-supervised models of spoken language
• Authors: Gaofei Shen, Michaela Watkins, Afra Alishahi, Arianna Bisazza, Grzegorz Chrupała,
• Abstract summary: This paper aims to analyze the tone encoding capabilities of Spoken Language Models (SLMs) We show that SLMs encode lexical tone to a significant degree even when they are trained on data from non-tonal languages. We find that SLMs behave similarly to native and non-native human participants in tone and consonant perception studies.
• Score: 3.7270979204213446
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Interpretability research has shown that self-supervised Spoken Language Models (SLMs) encode a wide variety of features in human speech from the acoustic, phonetic, phonological, syntactic and semantic levels, to speaker characteristics. The bulk of prior research on representations of phonology has focused on segmental features such as phonemes; the encoding of suprasegmental phonology (such as tone and stress patterns) in SLMs is not yet well understood. Tone is a suprasegmental feature that is present in more than half of the world's languages. This paper aims to analyze the tone encoding capabilities of SLMs, using Mandarin and Vietnamese as case studies. We show that SLMs encode lexical tone to a significant degree even when they are trained on data from non-tonal languages. We further find that SLMs behave similarly to native and non-native human participants in tone and consonant perception studies, but they do not follow the same developmental trajectory.

Related papers

• An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios [76.11409260727459]
  This paper explores the language adaptation capability of ZMM-TTS, a recent SSL-based multilingual TTS system. We demonstrate that the similarity in phonetics between the pre-training and target languages, as well as the language category, affects the target language's adaptation performance.
  arXiv  Detail & Related papers  (2024-06-13T08:16:52Z)
• PhonologyBench: Evaluating Phonological Skills of Large Language Models [57.80997670335227]
  Phonology, the study of speech's structure and pronunciation rules, is a critical yet often overlooked component in Large Language Model (LLM) research. We present PhonologyBench, a novel benchmark consisting of three diagnostic tasks designed to explicitly test the phonological skills of LLMs. We observe a significant gap of 17% and 45% on Rhyme Word Generation and Syllable counting, respectively, when compared to humans.
  arXiv  Detail & Related papers  (2024-04-03T04:53:14Z)
• How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics [33.070158866023]
  generative spoken language modeling (GSLM) involves using learned symbols derived from data rather than phonemes for speech analysis and synthesis. This paper presents the findings of GSLM's encoding and decoding effectiveness at the spoken-language and speech levels.
  arXiv  Detail & Related papers  (2023-06-01T14:07:19Z)
• Exploring How Generative Adversarial Networks Learn Phonological Representations [6.119392435448723]
  Generative Adversarial Networks (GANs) learn representations of phonological phenomena. We analyze how GANs encode contrastive and non-contrastive nasality in French and English vowels.
  arXiv  Detail & Related papers  (2023-05-21T16:37:21Z)
• Self-supervised models of audio effectively explain human cortical responses to speech [71.57870452667369]
  We capitalize on the progress of self-supervised speech representation learning to create new state-of-the-art models of the human auditory system. We show that these results show that self-supervised models effectively capture the hierarchy of information relevant to different stages of speech processing in human cortex.
  arXiv  Detail & Related papers  (2022-05-27T22:04:02Z)
• WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign Language [2.814213966364155]
  We build a large-scale dataset of American Sign Language signs annotated with six different phonological properties. We investigate whether data-driven end-to-end and feature-based approaches can be optimised to automatically recognise these properties.
  arXiv  Detail & Related papers  (2022-03-11T17:21:24Z)
• Cross-lingual Low Resource Speaker Adaptation Using Phonological Features [2.8080708404213373]
  We train a language-agnostic multispeaker model conditioned on a set of phonologically derived features common across different languages. With as few as 32 and 8 utterances of target speaker data, we obtain high speaker similarity scores and naturalness comparable to the corresponding literature.
  arXiv  Detail & Related papers  (2021-11-17T12:33:42Z)
• 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)
• A phonetic model of non-native spoken word processing [40.018538874161756]
  We train a computational model of phonetic learning, which has no access to phonology, on either one or two languages. We first show that the model exhibits predictable behaviors on phone-level and word-level discrimination tasks. We then test the model on a spoken word processing task, showing that phonology may not be necessary to explain some of the word processing effects observed in non-native speakers.
  arXiv  Detail & Related papers  (2021-01-27T11:46:21Z)
• How Phonotactics Affect Multilingual and Zero-shot ASR Performance [74.70048598292583]
  A Transformer encoder-decoder model has been shown to leverage multilingual data well in IPA transcriptions of languages presented during training. We replace the encoder-decoder with a hybrid ASR system consisting of a separate AM and LM. We show that the gain from modeling crosslingual phonotactics is limited, and imposing a too strong model can hurt the zero-shot transfer.
  arXiv  Detail & Related papers  (2020-10-22T23:07:24Z)
• Phonological Features for 0-shot Multilingual Speech Synthesis [50.591267188664666]
  We show that code-switching is possible for languages unseen during training, even within monolingual models. We generate intelligible, code-switched speech in a new language at test time, including the approximation of sounds never seen in training.
  arXiv  Detail & Related papers  (2020-08-06T18:25:18Z)

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.