Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0

• URL: http://arxiv.org/abs/2407.03005v1
• Date: Wed, 3 Jul 2024 11:04:31 GMT
• Title: Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0
• Authors: Marianne de Heer Kloots, Willem Zuidema,
• Abstract summary: We study how Wav2Vec2 resolves phonotactic constraints. We synthesize sounds on an acoustic continuum between /l/ and /r/ and embed them in controlled contexts. Like humans, Wav2Vec2 models show a bias towards the phonotactically admissable category in processing such ambiguous sounds.
• Score: 0.11510009152620666
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: What do deep neural speech models know about phonology? Existing work has examined the encoding of individual linguistic units such as phonemes in these models. Here we investigate interactions between units. Inspired by classic experiments on human speech perception, we study how Wav2Vec2 resolves phonotactic constraints. We synthesize sounds on an acoustic continuum between /l/ and /r/ and embed them in controlled contexts where only /l/, only /r/, or neither occur in English. Like humans, Wav2Vec2 models show a bias towards the phonotactically admissable category in processing such ambiguous sounds. Using simple measures to analyze model internals on the level of individual stimuli, we find that this bias emerges in early layers of the model's Transformer module. This effect is amplified by ASR finetuning but also present in fully self-supervised models. Our approach demonstrates how controlled stimulus designs can help localize specific linguistic knowledge in neural speech models.

Related papers

• Perception of Phonological Assimilation by Neural Speech Recognition Models [3.4173734484549625]
  This article explores how the neural speech recognition model Wav2Vec2 perceives assimilated sounds. Using psycholinguistic stimuli, we analyze how various linguistic context cues influence compensation patterns in the model's output.
  arXiv  Detail & Related papers  (2024-06-21T15:58:22Z)
• 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)
• Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias [71.94109664001952]
  Mega-TTS is a novel zero-shot TTS system that is trained with large-scale wild data. We show that Mega-TTS surpasses state-of-the-art TTS systems on zero-shot TTS speech editing, and cross-lingual TTS tasks.
  arXiv  Detail & Related papers  (2023-06-06T08:54:49Z)
• A unified one-shot prosody and speaker conversion system with self-supervised discrete speech units [94.64927912924087]
  Existing systems ignore the correlation between prosody and language content, leading to degradation of naturalness in converted speech. We devise a cascaded modular system leveraging self-supervised discrete speech units as language representation. Experiments show that our system outperforms previous approaches in naturalness, intelligibility, speaker transferability, and prosody transferability.
  arXiv  Detail & Related papers  (2022-11-12T00:54:09Z)
• Is neural language acquisition similar to natural? A chronological probing study [0.0515648410037406]
  We present the chronological probing study of transformer English models such as MultiBERT and T5. We compare the information about the language learned by the models in the process of training on corpora. The results show that 1) linguistic information is acquired in the early stages of training 2) both language models demonstrate capabilities to capture various features from various levels of language.
  arXiv  Detail & Related papers  (2022-07-01T17:24:11Z)
• Toward a realistic model of speech processing in the brain with self-supervised learning [67.7130239674153]
  Self-supervised algorithms trained on the raw waveform constitute a promising candidate. We show that Wav2Vec 2.0 learns brain-like representations with as little as 600 hours of unlabelled speech.
  arXiv  Detail & Related papers  (2022-06-03T17:01:46Z)
• Do self-supervised speech models develop human-like perception biases? [11.646802225841153]
  We examine the representational spaces of three kinds of state-of-the-art self-supervised models: wav2vec 2.0, HuBERT and contrastive predictive coding ( CPC) We show that the CPC model shows a small native language effect, but that wav2vec 2.0 and HuBERT seem to develop a universal speech perception space which is not language specific. A comparison against the predictions of supervised phone recognisers suggests that all three self-supervised models capture relatively fine-grained perceptual phenomena, while supervised models are better at capturing coarser, phone-level, effects of listeners' native language, on perception.
  arXiv  Detail & Related papers  (2022-05-31T14:21:40Z)
• 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)
• 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)
• What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure [64.54208910952651]
  We compare audio transformer models Mockingjay and wave2vec2.0. We probe the audio models' understanding of textual surface, syntax, and semantic features. We do this over exhaustive settings for native, non-native, synthetic, read and spontaneous speech datasets.
  arXiv  Detail & Related papers  (2021-01-02T06:29:12Z)

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.