Why We Need Speech to Evaluate Speech Translation

• URL: http://arxiv.org/abs/2605.28227v1
• Date: Wed, 27 May 2026 09:41:22 GMT
• Title: Why We Need Speech to Evaluate Speech Translation
• Abstract summary: We evaluate both text- and speech-based quality estimation metrics.<n>We find that both fall short, even when given direct access to the speech signal.<n>We identify three causes: (1) speech-specific features are not reliably preserved in current encoders, (2) models tend to ignore the speech source signal, and (3) quality estimation training data contains too few relevant examples.
• Score: 32.52881174671332
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Speech translation models are increasingly capable of preserving speech-specific information (e.g., speaker gender, prosody, and emphasis), yet evaluation metrics remain blind to such phenomena. We meta-evaluate both text- and speech-based quality estimation metrics on two contrastive datasets targeting gender agreement and prosody, and find that both fall short, even when given direct access to the speech signal. We then train SpeechCOMET, a family of quality estimation models with speech encoders, and evaluate a state-of-the-art SpeechLLM as a judge. Both match or exceed text-based COMET on standard quality estimation, but neither consistently assesses speech-specific phenomena. We identify three causes: (1) speech-specific features are not reliably preserved in current encoders, (2) models tend to ignore the speech source signal, and (3) quality estimation training data contains too few relevant examples. We release all models and code, and argue that progress requires dedicated speech-specific training data and models that genuinely condition on speech.

Related papers

• Quantifying the Generation Modality Gap in Speech-Text Language Models [22.8588553114451]
  Pure speech language models often lag behind text and speech-text language models in generating coherent content.<n>We study the speech-text modality gap in a family of spoken language models, based on flow matching for continuous acoustic feature generation.<n>We construct a unified generation-based evaluation suite that compares speech-only, text-only, and speech-text language models trained on matched data.
  arXiv  Detail & Related papers  (2026-09-13T19:09:07Z)
• SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models [60.72029578488467]
  SpeechR is a unified benchmark for evaluating reasoning over speech in large audio-language models.<n>It evaluates models along three key dimensions: factual retrieval, procedural inference, and normative judgment.<n> Evaluations on eleven state-of-the-art LALMs reveal that high transcription accuracy does not translate into strong reasoning capabilities.
  arXiv  Detail & Related papers  (2025-08-04T03:28:04Z)
• S2S-Arena, Evaluating Speech2Speech Protocols on Instruction Following with Paralinguistic Information [47.950757976473035]
  We introduce S2S-Arena, a novel arena-style S2S benchmark that evaluates instruction-following capabilities with paralinguistic information.<n>In addition to the superior performance of GPT-4o, the speech model of cascaded ASR, LLM, and TTS outperforms the jointly trained model after text-speech alignment in speech2speech protocols.
  arXiv  Detail & Related papers  (2025-03-07T02:07:00Z)
• Scaling Speech-Text Pre-training with Synthetic Interleaved Data [31.77653849518526]
  Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction.<n>Traditional approaches for developing SpeechLMs are constrained by the limited availability of unsupervised speech data and parallel speech-text data.<n>We propose a novel approach to scaling speech-text pre-training by leveraging large-scale synthetic interleaved data derived from text corpora.
  arXiv  Detail & Related papers  (2024-11-26T17:19:09Z)
• SpeechLMScore: Evaluating speech generation using speech language model [43.20067175503602]
  We propose SpeechLMScore, an unsupervised metric to evaluate generated speech using a speech-language model. It does not require human annotation and is a highly scalable framework. Evaluation results demonstrate that the proposed metric shows a promising correlation with human evaluation scores on different speech generation tasks.
  arXiv  Detail & Related papers  (2022-12-08T21:00:15Z)
• SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data [100.46303484627045]
  We propose a cross-modal Speech and Language Model (SpeechLM) to align speech and text pre-training with a pre-defined unified representation. Specifically, we introduce two alternative discrete tokenizers to bridge the speech and text modalities. We evaluate SpeechLM on various spoken language processing tasks including speech recognition, speech translation, and universal representation evaluation framework SUPERB.
  arXiv  Detail & Related papers  (2022-09-30T09:12:10Z)
• 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)
• VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion [54.29557210925752]
  One-shot voice conversion can be effectively achieved by speech representation disentanglement. We employ vector quantization (VQ) for content encoding and introduce mutual information (MI) as the correlation metric during training. Experimental results reflect the superiority of the proposed method in learning effective disentangled speech representations.
  arXiv  Detail & Related papers  (2021-06-18T13:50:38Z)
• Leveraging Pre-trained Language Model for Speech Sentiment Analysis [58.78839114092951]
  We explore the use of pre-trained language models to learn sentiment information of written texts for speech sentiment analysis. We propose a pseudo label-based semi-supervised training strategy using a language model on an end-to-end speech sentiment approach.
  arXiv  Detail & Related papers  (2021-06-11T20:15:21Z)
• Generative Spoken Language Modeling from Raw Audio [42.153136032037175]
  Generative spoken language modeling involves learning jointly the acoustic and linguistic characteristics of a language from raw audio only (without text or labels) We introduce metrics to automatically evaluate the generated output in terms of acoustic and linguistic quality in two associated end-to-end tasks. We test baseline systems consisting of a discrete speech encoder (returning discrete, low, pseudo-text units), a generative language model (trained on pseudo-text units) and a speech decoder.
  arXiv  Detail & Related papers  (2021-02-01T21:41:40Z)

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.