Seeing isn't Hearing: Benchmarking Vision Language Models at Interpreting Spectrograms

• URL: http://arxiv.org/abs/2511.13225v1
• Date: Mon, 17 Nov 2025 10:41:07 GMT
• Title: Seeing isn't Hearing: Benchmarking Vision Language Models at Interpreting Spectrograms
• Authors: Tyler Loakman, Joseph James, Chenghua Lin,
• Abstract summary: We benchmark the extent to which VLMs are able to act as highly-trained phoneticians.<n>We synthesise a novel dataset containing 4k+ English words spoken in isolation alongside stylistically consistent spectrogram and waveform figures.
• Score: 21.197328006274578
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rise of Large Language Models (LLMs) and their vision-enabled counterparts (VLMs), numerous works have investigated their capabilities in tasks that fuse the modalities of vision and language. In this work, we benchmark the extent to which VLMs are able to act as highly-trained phoneticians, interpreting spectrograms and waveforms of speech. To do this, we synthesise a novel dataset containing 4k+ English words spoken in isolation alongside stylistically consistent spectrogram and waveform figures. We test the ability of VLMs to understand these representations of speech through a multiple-choice task whereby models must predict the correct phonemic or graphemic transcription of a spoken word when presented amongst 3 distractor transcriptions that have been selected based on their phonemic edit distance to the ground truth. We observe that both zero-shot and finetuned models rarely perform above chance, demonstrating the requirement for specific parametric knowledge of how to interpret such figures, rather than paired samples alone.

Related papers

• ELEGANCE: Efficient LLM Guidance for Audio-Visual Target Speech Extraction [88.41471266579333]
  We propose ELEGANCE, a novel framework that incorporates linguistic knowledge from large language models (LLMs) into AV-TSE models.<n> Comprehensive experiments with RoBERTa, Qwen3-0.6B, and Qwen3-4B on two AV-TSE backbones show significant improvements.
  arXiv  Detail & Related papers  (2025-11-09T08:50:11Z)
• VALLR: Visual ASR Language Model for Lip Reading [28.561566996686484]
  Lip Reading, or Visual Automatic Speech Recognition, is a complex task requiring the interpretation of spoken language exclusively from visual cues.<n>We propose a novel two-stage, phoneme-centric framework for Visual Automatic Speech Recognition (V-ASR)<n>First, our model predicts a compact sequence of phonemes from visual inputs using a Video Transformer with a CTC head.<n>This phoneme output then serves as the input to a fine-tuned Large Language Model (LLM), which reconstructs coherent words and sentences.
  arXiv  Detail & Related papers  (2025-03-27T11:52:08Z)
• Vision-Speech Models: Teaching Speech Models to Converse about Images [67.62394024470528]
  We introduce MoshiVis, augmenting a recent dialogue speech LLM, Moshi, with visual inputs through lightweight adaptation modules.<n>An additional dynamic gating mechanism enables the model to more easily switch between the visual inputs and unrelated conversation topics.<n>We evaluate the model on downstream visual understanding tasks with both audio and text prompts, and report qualitative samples of interactions with MoshiVis.
  arXiv  Detail & Related papers  (2025-03-19T18:40:45Z)
• Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing [56.71450690166821]
  We propose a novel framework, namely Visual Speech Processing incorporated with LLMs (VSP-LLM) VSP-LLM is designed to perform multi-tasks of visual speech recognition and translation. We show that VSP-LLM trained on just 30 hours of labeled data can more effectively translate lip movements.
  arXiv  Detail & Related papers  (2024-02-23T07:21:32Z)
• 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)
• VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning [119.49605266839053]
  We propose a unified cross-modal representation learning framework VATLM (Visual-Audio-Text Language Model) The proposed VATLM employs a unified backbone network to model the modality-independent information. In order to integrate these three modalities into one shared semantic space, VATLM is optimized with a masked prediction task of unified tokens.
  arXiv  Detail & Related papers  (2022-11-21T09:10:10Z)
• 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)
• Direct speech-to-speech translation with discrete units [64.19830539866072]
  We present a direct speech-to-speech translation (S2ST) model that translates speech from one language to speech in another language without relying on intermediate text generation. We propose to predict the self-supervised discrete representations learned from an unlabeled speech corpus instead. When target text transcripts are available, we design a multitask learning framework with joint speech and text training that enables the model to generate dual mode output (speech and text) simultaneously in the same inference pass.
  arXiv  Detail & Related papers  (2021-07-12T17:40:43Z)
• STEPs-RL: Speech-Text Entanglement for Phonetically Sound Representation Learning [2.28438857884398]
  We present a novel multi-modal deep neural network architecture that uses speech and text entanglement for learning spoken-word representations. STEPs-RL is trained in a supervised manner to predict the phonetic sequence of a target spoken-word. Latent representations produced by our model were able to predict the target phonetic sequences with an accuracy of 89.47%.
  arXiv  Detail & Related papers  (2020-11-23T13:29:16Z)

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.