Revisiting Direct Speech-to-Text Translation with Speech LLMs: Better Scaling than CoT Prompting?

• URL: http://arxiv.org/abs/2510.03093v1
• Date: Fri, 03 Oct 2025 15:23:32 GMT
• Title: Revisiting Direct Speech-to-Text Translation with Speech LLMs: Better Scaling than CoT Prompting?
• Authors: Oriol Pareras, Gerard I. Gállego, Federico Costa, Cristina España-Bonet, Javier Hernando,
• Abstract summary: We systematically compare Chain-of-Thought (CoT) and Direct prompting under increasing amounts of Speech-to-Text Translation (S2TT) data.<n>Our results show that Direct improves more consistently as the amount of data increases, suggesting that it may become a more effective approach as larger S2TT resources are created.
• Score: 13.202203902821333
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work on Speech-to-Text Translation (S2TT) has focused on LLM-based models, introducing the increasingly adopted Chain-of-Thought (CoT) prompting, where the model is guided to first transcribe the speech and then translate it. CoT typically outperforms direct prompting primarily because it can exploit abundant Automatic Speech Recognition (ASR) and Text-to-Text Translation (T2TT) datasets to explicitly model its steps. In this paper, we systematically compare CoT and Direct prompting under increasing amounts of S2TT data. To this end, we pseudo-label an ASR corpus by translating its transcriptions into six European languages, and train LLM-based S2TT systems with both prompting strategies at different data scales. Our results show that Direct improves more consistently as the amount of data increases, suggesting that it may become a more effective approach as larger S2TT resources are created.

Related papers

• Direct Simultaneous Translation Activation for Large Audio-Language Models [58.03785696031301]
  Simultaneous speech-to-text translation (Simul-S2TT) aims to translate speech into target text in real time.<n>We introduce bf Simultaneous bf Self-bf Augmentation (bf SimulSA), a strategy that utilizes LALMs' inherent capabilities to obtain simultaneous data.
  arXiv  Detail & Related papers  (2025-09-19T07:12:18Z)
• GOAT-TTS: Expressive and Realistic Speech Generation via A Dual-Branch LLM [42.93855899824886]
  We propose a text-to-speech generation approach optimized via a novel dual-branch ArchiTecture (GOAT-TTS)<n>GOAT-TTS combines a speech encoder and projector to capture continuous acoustic embeddings, enabling bidirectional correlation between paralinguistic features (language, timbre, emotion) and semantic text representations without transcript dependency.<n> Experimental results demonstrate that our GOAT-TTS achieves performance comparable to state-of-the-art TTS models.
  arXiv  Detail & Related papers  (2025-04-15T01:44:56Z)
• Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning [32.883836078329665]
  Multimodal Large Language Models (MLLMs) have achieved significant success in Speech-to-Text Translation (S2TT) tasks.<n>We propose a three-stage curriculum learning strategy that leverages the machine translation capabilities of large language models and adapts them to S2TT tasks.<n> Experimental results show that the proposed strategy achieves state-of-the-art average performance in $15times14$ language pairs.
  arXiv  Detail & Related papers  (2024-09-29T01:48:09Z)
• SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models [64.40250409933752]
  We build upon our previous publication by implementing a simple and efficient non-autoregressive (NAR) TTS framework, termed SimpleSpeech 2. SimpleSpeech 2 effectively combines the strengths of both autoregressive (AR) and non-autoregressive (NAR) methods. We show a significant improvement in generation performance and generation speed compared to our previous work and other state-of-the-art (SOTA) large-scale TTS models.
  arXiv  Detail & Related papers  (2024-08-25T17:07:39Z)
• Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data? [49.42189569058647]
  Two-pass direct speech-to-speech translation (S2ST) models decompose the task into speech-to-text translation (S2TT) and text-to-speech (TTS) In this paper, we introduce a composite S2ST model named ComSpeech, which can seamlessly integrate any pretrained S2TT and TTS models into a direct S2ST model. We also propose a novel training method ComSpeech-ZS that solely utilizes S2TT and TTS data.
  arXiv  Detail & Related papers  (2024-06-11T14:17:12Z)
• Back Translation for Speech-to-text Translation Without Transcripts [11.13240570688547]
  We develop a back translation algorithm for ST (BT4ST) to synthesize pseudo ST data from monolingual target data. To ease the challenges posed by short-to-long generation and one-to-many mapping, we introduce self-supervised discrete units. With our synthetic ST data, we achieve an average boost of 2.3 BLEU on MuST-C En-De, En-Fr, and En-Es datasets.
  arXiv  Detail & Related papers  (2023-05-15T15:12:40Z)
• Enhancing Speech-to-Speech Translation with Multiple TTS Targets [62.18395387305803]
  We analyze the effect of changing synthesized target speech for direct S2ST models. We propose a multi-task framework that jointly optimized the S2ST system with multiple targets from different TTS systems.
  arXiv  Detail & Related papers  (2023-04-10T14:33:33Z)
• Code-Switching Text Generation and Injection in Mandarin-English ASR [57.57570417273262]
  We investigate text generation and injection for improving the performance of an industry commonly-used streaming model, Transformer-Transducer (T-T) We first propose a strategy to generate code-switching text data and then investigate injecting generated text into T-T model explicitly by Text-To-Speech (TTS) conversion or implicitly by tying speech and text latent spaces. Experimental results on the T-T model trained with a dataset containing 1,800 hours of real Mandarin-English code-switched speech show that our approaches to inject generated code-switching text significantly boost the performance of T-T models.
  arXiv  Detail & Related papers  (2023-03-20T09:13:27Z)
• Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation [76.13334392868208]
  Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues. In this work, we explore self-supervised pre-training with unlabeled speech data and data augmentation to tackle this issue.
  arXiv  Detail & Related papers  (2022-04-06T17:59:22Z)
• Incremental Speech Synthesis For Speech-To-Speech Translation [23.951060578077445]
  We focus on improving the incremental synthesis performance of TTS models. With a simple data augmentation strategy based on prefixes, we are able to improve the incremental TTS quality to approach offline performance. We propose latency metrics tailored to S2ST applications, and investigate methods for latency reduction in this context.
  arXiv  Detail & Related papers  (2021-10-15T17:20:28Z)

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.