arXiv:2610.35042v1 Announce Type: new Abstract: Simultaneous speech translation (SimulST) aims to translate ongoing speech with low latency while preserving translation quality. Recent studies have a...
arXiv:2504.11809v2 Announce Type: replace Abstract: Simultaneous speech translation (SimulST) produces translations incrementally while processing partial speech input. Although large language models...
arXiv:2509.21932v3 Announce Type: replace Abstract: How to make human-interpreter-like read/write decisions for simultaneous speech translation (SimulST) systems? Current state-of-the-art systems for...
The paper presents a method for improving simultaneous speech translation by adapting a full‑utterance speech language model with prefix supervision derived from its own complete and partial waveform translations, eliminating the need for transcripts or human translations. Experiments on FLEURS and CoVoST2 across three language directions show that prefix training enhances quality–latency trade‑offs, especially when combined with multi‑turn append‑only decoding, and that a confidence threshold effectively controls the inference‑time quality–latency balance. The study also explores the impact of synthesis margin on translation quality and calibration, finding a non‑monotonic relationship with latency.
The paper introduces a training strategy for cascaded simultaneous speech translation that allows the system to dynamically decide how much of the source prefix to translate. By fine‑tuning a large language model (Qwen3‑8B) on stable prefixes—pairs of source prefixes and the longest shared translation with the full sentence—the authors enable contextual read‑write decisions beyond fixed wait‑k or target‑suffix deletion. Experiments on English‑to‑German, Japanese, and Chinese demonstrate that stable prefixes improve the quality‑latency tradeoff across various test sets.
The paper introduces a method called randomized intermediate guidance for training tandem speech-to-speech models, where a large language model (LLM) acts as a backend providing candidate responses while the user is speaking. Instead of simulating the backend’s guidance, the approach derives guidance directly from the conversation corpus, using target responses for informative guidance and randomly sampled responses to simulate irrelevant updates. Experiments on synthetic dialogues and 3.8k hours of real conversations show that this technique yields response quality comparable to LLM-generated baselines while improving natural turn‑taking and audio‑judge naturalness.
DIAL‑S2ST is a post‑training method that learns to control inference‑time latency in simultaneous speech‑to‑speech translation models. It reuses pretrained translation capabilities through self‑distillation from lookahead predictions and limits large text distillation losses to address the imitation gap, providing supervision for earlier emission without paired target data or reward computation. By jointly training a single LoRA adapter across scales with matched lookahead guidance, the learned timing can be adjusted at inference, and experiments on French‑to‑English translation with Hibiki show that only 10 hours of source speech enable this adaptation, yielding flexible latency control with a favorable quality‑latency trade‑off.
The paper introduces FAST-CAP, a causality‑aware framework for simultaneous speech‑to‑speech translation that combines a factorized S2ST architecture, an adaptive policy, and a new latency metric. It employs a novel data pipeline to generate high‑fidelity, causally aligned segments, improving voice transfer and reducing the need for large training datasets. Experiments on Spanish, German, and French demonstrate that FAST‑CAP outperforms fixed‑policy baselines, achieving up to +1.2 BLEU, 26% lower latency, and a 38.8% relative latency reduction while maintaining speaker fidelity.
CoSTA is a post‑hoc framework that decouples the generation and synthesis token spaces in Spoken Dialogue Models, allowing the use of compressed speech tokens for faster generation while preserving the original tokenizer and decoder. It extends the generation token space with compressed representations through mean‑initialized vocabulary extension, pronunciation adaptation, and dialogue adaptation, then deterministically expands back to the original token space for synthesis. Experiments on bilingual speech‑dialogue benchmarks show about 1.7× faster generation, lower latency, higher throughput, and maintained response quality, with a practical trade‑off between compression, decoding efficiency, and quality.
X-Translator is a low‑cost, modular real‑time speech‑to‑speech translation system that integrates streaming ASR, machine translation, and prompt‑conditioned TTS, managed by a session‑level runtime controller. It uses incremental segment commitment to stabilize ASR streams and an online speaker prompt manager to maintain speaker consistency across multi‑speaker conversations. The system is evaluated on translation quality, speech naturalness, latency, and speaker preservation using OpenSTBench, and its code and demo are publicly available on GitHub.
The paper introduces AZeroS, a speech‑adapted large language model that uses Self‑Generated Instruction‑Free Tuning (SIFT) to avoid task‑specific instruction data. By training only two lightweight projection modules on 25,000 hours of speech‑text pairs and 3,000 hours of paralinguistic labels, AZeroS achieves state‑of‑the‑art results on semantic and paralinguistic benchmarks while keeping the core LLM and audio encoder frozen.
Simulstream is an open‑source toolkit designed to evaluate and demonstrate streaming speech‑to‑text translation systems. It supports both incremental and re‑translation decoding on long‑form speech, offers fine‑grained logging for quality and latency metrics, and includes an interactive web interface for real‑time visualization and comparison. The toolkit addresses the fragmented evaluation landscape by providing a unified framework that accommodates different decoding strategies and input formats.