Which Evaluation for Which Model? A Taxonomy for Speech Model Assessment

• URL: http://arxiv.org/abs/2510.19509v1
• Date: Wed, 22 Oct 2025 12:04:32 GMT
• Title: Which Evaluation for Which Model? A Taxonomy for Speech Model Assessment
• Authors: Maureen de Seyssel, Eeshan Gunesh Dhekane,
• Abstract summary: Speech foundation models have recently achieved remarkable capabilities across a wide range of tasks.<n>Different models excel at distinct aspects of speech processing and thus require different evaluation protocols.<n>This paper proposes a unified taxonomy that addresses the question: Which evaluation is appropriate for which model?
• Score: 3.6991820768985746
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Speech foundation models have recently achieved remarkable capabilities across a wide range of tasks. However, their evaluation remains disjointed across tasks and model types. Different models excel at distinct aspects of speech processing and thus require different evaluation protocols. This paper proposes a unified taxonomy that addresses the question: Which evaluation is appropriate for which model? The taxonomy defines three orthogonal axes: the \textbf{evaluation aspect} being measured, the model capabilities required to attempt the task, and the task or protocol requirements needed to perform it. We classify a broad set of existing evaluations and benchmarks along these axes, spanning areas such as representation learning, speech generation, and interactive dialogue. By mapping each evaluation to the capabilities a model exposes (e.g., speech generation, real-time processing) and to its methodological demands (e.g., fine-tuning data, human judgment), the taxonomy provides a principled framework for aligning models with suitable evaluation methods. It also reveals systematic gaps, such as limited coverage of prosody, interaction, or reasoning, that highlight priorities for future benchmark design. Overall, this work offers a conceptual foundation and practical guide for selecting, interpreting, and extending evaluations of speech models.

Related papers

• On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation [88.77441715819366]
  Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content.<n>We propose a variety of likelihood- and generative-based evaluation methods that serve in place of naive global token perplexity.
  arXiv  Detail & Related papers  (2026-01-09T22:01:56Z)
• Adapting Vision-Language Models for Evaluating World Models [24.813041196394582]
  We present UNIVERSE, a method for adapting Vision-language Evaluator for Rollouts in Simulated Environments under data and compute constraints.<n>We conduct a large-scale study comparing full, partial, and parameter-efficient finetuning across task formats, context lengths, sampling strategies, and data compositions.<n>The resulting unified evaluator matches the performance of task-specific baselines using a single checkpoint.
  arXiv  Detail & Related papers  (2025-06-22T09:53:28Z)
• LLM Reading Tea Leaves: Automatically Evaluating Topic Models with Large Language Models [12.500091504010067]
  We propose WALM (Word Agreement with Language Model), a new evaluation method for topic modeling.<n>With extensive experiments involving different types of topic models, WALM is shown to align with human judgment.
  arXiv  Detail & Related papers  (2024-06-13T11:19:50Z)
• Detecting Statements in Text: A Domain-Agnostic Few-Shot Solution [1.3654846342364308]
  State-of-the-art approaches usually involve fine-tuning models on large annotated datasets, which are costly to produce. We propose and release a qualitative and versatile few-shot learning methodology as a common paradigm for any claim-based textual classification task. We illustrate this methodology in the context of three tasks: climate change contrarianism detection, topic/stance classification and depression-relates symptoms detection.
  arXiv  Detail & Related papers  (2024-05-09T12:03:38Z)
• Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy [27.454549324141087]
  We propose a novel VQA benchmark based on well-known visual classification datasets. We also suggest using the semantic hierarchy of the label space to ask automatically generated follow-up questions about the ground-truth category. Our contributions aim to lay the foundation for more precise and meaningful assessments.
  arXiv  Detail & Related papers  (2024-02-11T18:26:18Z)
• FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets [69.91340332545094]
  We introduce FLASK, a fine-grained evaluation protocol for both human-based and model-based evaluation. We experimentally observe that the fine-graininess of evaluation is crucial for attaining a holistic view of model performance.
  arXiv  Detail & Related papers  (2023-07-20T14:56:35Z)
• How to Estimate Model Transferability of Pre-Trained Speech Models? [84.11085139766108]
  "Score-based assessment" framework for estimating transferability of pre-trained speech models. We leverage upon two representation theories, Bayesian likelihood estimation and optimal transport, to generate rank scores for the PSM candidates. Our framework efficiently computes transferability scores without actual fine-tuning of candidate models or layers.
  arXiv  Detail & Related papers  (2023-06-01T04:52:26Z)
• Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue [92.01165203498299]
  Embodied dialogue instruction following requires an agent to complete a complex sequence of tasks from a natural language exchange. This paper argues that imitation learning (IL) and related low-level metrics are actually misleading and do not align with the goals of embodied dialogue research.
  arXiv  Detail & Related papers  (2022-10-10T05:51:40Z)
• GODEL: Large-Scale Pre-Training for Goal-Directed Dialog [119.1397031992088]
  We introduce GODEL, a large pre-trained language model for dialog. We show that GODEL outperforms state-of-the-art pre-trained dialog models in few-shot fine-tuning setups. A novel feature of our evaluation methodology is the introduction of a notion of utility that assesses the usefulness of responses.
  arXiv  Detail & Related papers  (2022-06-22T18:19:32Z)
• Probing Task-Oriented Dialogue Representation from Language Models [106.02947285212132]
  This paper investigates pre-trained language models to find out which model intrinsically carries the most informative representation for task-oriented dialogue tasks. We fine-tune a feed-forward layer as the classifier probe on top of a fixed pre-trained language model with annotated labels in a supervised way.
  arXiv  Detail & Related papers  (2020-10-26T21:34:39Z)

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.