Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment

• URL: http://arxiv.org/abs/2503.19586v1
• Date: Tue, 25 Mar 2025 12:10:47 GMT
• Title: Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment
• Authors: Hanlin Wu, Xufeng Duan, Zhenguang Cai,
• Abstract summary: This study compares how large audio-language models (LALMs) and humans integrate speaker characteristics during speech comprehension.<n>We compared two LALMs' (Qwen2-Audio and Ultravox 0.5) processing patterns with human EEG responses.
• Score: 0.846600473226587
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Voice-based AI development faces unique challenges in processing both linguistic and paralinguistic information. This study compares how large audio-language models (LALMs) and humans integrate speaker characteristics during speech comprehension, asking whether LALMs process speaker-contextualized language in ways that parallel human cognitive mechanisms. We compared two LALMs' (Qwen2-Audio and Ultravox 0.5) processing patterns with human EEG responses. Using surprisal and entropy metrics from the models, we analyzed their sensitivity to speaker-content incongruency across social stereotype violations (e.g., a man claiming to regularly get manicures) and biological knowledge violations (e.g., a man claiming to be pregnant). Results revealed that Qwen2-Audio exhibited increased surprisal for speaker-incongruent content and its surprisal values significantly predicted human N400 responses, while Ultravox 0.5 showed limited sensitivity to speaker characteristics. Importantly, neither model replicated the human-like processing distinction between social violations (eliciting N400 effects) and biological violations (eliciting P600 effects). These findings reveal both the potential and limitations of current LALMs in processing speaker-contextualized language, and suggest differences in social-linguistic processing mechanisms between humans and LALMs.

Related papers

• Audio Large Language Models Can Be Descriptive Speech Quality Evaluators [46.765203628127345]
  We introduce the first natural language-based speech evaluation corpus, generated from authentic human ratings. This corpus offers detailed analysis across multiple dimensions and identifies causes of quality degradation. We propose an alignment approach with LLM distillation (ALLD) to guide the audio LLM in extracting relevant information from raw speech.
  arXiv  Detail & Related papers  (2025-01-27T22:47:51Z)
• Cross-lingual Speech Emotion Recognition: Humans vs. Self-Supervised Models [16.0617753653454]
  This study presents a comparative analysis between human performance and SSL models. We also compare the SER ability of models and humans at both utterance- and segment-levels. Our findings reveal that models, with appropriate knowledge transfer, can adapt to the target language and achieve performance comparable to native speakers.
  arXiv  Detail & Related papers  (2024-09-25T13:27:17Z)
• SIFToM: Robust Spoken Instruction Following through Theory of Mind [51.326266354164716]
  We present a cognitively inspired model, Speech Instruction Following through Theory of Mind (SIFToM), to enable robots to pragmatically follow human instructions under diverse speech conditions. Results show that the SIFToM model outperforms state-of-the-art speech and language models, approaching human-level accuracy on challenging speech instruction following tasks.
  arXiv  Detail & Related papers  (2024-09-17T02:36:10Z)
• Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation [71.31331402404662]
  This paper proposes two novel data-efficient methods to learn dysarthric and elderly speaker-level features. Speaker-regularized spectral basis embedding-SBE features that exploit a special regularization term to enforce homogeneity of speaker features in adaptation. Feature-based learning hidden unit contributions (f-LHUC) that are conditioned on VR-LH features that are shown to be insensitive to speaker-level data quantity in testtime adaptation.
  arXiv  Detail & Related papers  (2024-07-08T18:20:24Z)
• Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0 [0.11510009152620666]
  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.
  arXiv  Detail & Related papers  (2024-07-03T11:04:31Z)
• 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)
• Divergences between Language Models and Human Brains [59.100552839650774]
  We systematically explore the divergences between human and machine language processing.<n>We identify two domains that LMs do not capture well: social/emotional intelligence and physical commonsense.<n>Our results show that fine-tuning LMs on these domains can improve their alignment with human brain responses.
  arXiv  Detail & Related papers  (2023-11-15T19:02:40Z)
• 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)
• 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)
• 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)
• Model-based analysis of brain activity reveals the hierarchy of language in 305 subjects [82.81964713263483]
  A popular approach to decompose the neural bases of language consists in correlating, across individuals, the brain responses to different stimuli. Here, we show that a model-based approach can reach equivalent results within subjects exposed to natural stimuli.
  arXiv  Detail & Related papers  (2021-10-12T15:30:21Z)

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.