arXiv Computation and Language

DIAL-S2ST: Learning Latency Control for Simultaneous Speech-to-Speech Translation

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.

arXiv Computation and Language

Sep 11

Streaming Translation and Transcription Through Speech-to-Text Causal Alignment

The paper introduces Hikari, a policy‑free, end‑to‑end model that performs simultaneous speech‑to‑text translation and streaming transcription. It employs a Decoder Time Dilation mechanism to mitigate overuse of WAIT tokens during training and a supervised fine‑tuning strategy that helps the model recover from delays, improving the quality‑latency trade‑off. Despite its modest size, Hikari achieves competitive translation quality at consistently low latency, outperforming larger published IWSLT 2026 submissions and proprietary API systems on en‑ja, en‑de, and en‑ru tasks.

By Roman Koshkin, Jeon Haesung, Lianbo Liu, Hao Shi, Mengjie Zhao, Yusuke Fujita, Yui Sudo

nlp fine-tuning safety

arXiv Computation and Language

Sep 28

All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation

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.

By Amir Hussein, Enas Albasiri, Travis M. Bartley, Nourchene Ferchichi, Ke Hu, Harishchandra Dubey, Myungjong Kim, Zhehuai Chen, Oluwatobi Olabiyi, Sanjeev Khudanpur

llms benchmarks data-engineering

arXiv Computation and Language

Oct 5

Learning When to Commit from Partial Speech for End-to-End Simultaneous Speech Translation

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.

By Hieu Hoang, Amittai Axelrod

llms

arXiv Computation and Language

Sep 22

Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture

arXiv:2504.11809v2 Announce Type: replace Abstract: Simultaneous speech translation (SimulST) produces translations incrementally while processing partial speech input. Although large language models...

By Biao Fu, Donglei Yu, Minpeng Liao, Chengxi Li, Xinjie Chen, Yidong Chen, Kai Fan, Xiaodong Shi

llms

arXiv Computation and Language

1d ago

SimPOTrans: Self-Adaptation for Offline-to-Simultaneous Speech Translation via Reinforcement Learning

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...

By Haotian Tan, Hiroki Ouchi, Sakriani Sakti

llms reinforcement-learning benchmarks

arXiv AI

Jun 24

WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models

arXiv:2604. 08558v2 Announce Type: replace-cross Abstract: Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention.

By Hanna Lee, Tan Dat Nguyen, Jaehoon Kang, Kyuhong Shim

fine-tuning efficiency multimodal

Hugging Face Trending Papers

Aug 3

The Role of Disfluencies in Speech Translation

Current speech translation systems, including SpeechLLMs, are trained on cleaned text and tend to strip disfluencies like filled pauses and false starts rather than translate them. We show this comes at a cost: disfluencies carry meaning that gets lost when speech is cleaned up.

benchmarks

arXiv AI

Jun 12

NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation

arXiv:2606. 13121v1 Announce Type: cross Abstract: Simultaneous speech-to-speech translation aims to enable near-real-time communication by minimizing latency, offering a compelling, real-time alternative to the high latency of consecutive translation.

By Dongwook Lee, Youngho Cho, Sangkwon Park, Heeseung Kim, Sungroh Yoon

benchmarks

arXiv AI

Jun 15

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs

arXiv:2603. 24596v3 Announce Type: replace-cross Abstract: While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based counterparts.

By Di Cao, Dongjie Fu, Hai Yu, Siqi Zheng, Xu Tan, Tao Jin

llms reinforcement-learning fine-tuning efficiency multimodal benchmarks safety

arXiv AI

Aug 11

CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents

arXiv:2608. 08638v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools.

By Yuqian Zhang, Yao Shi, Kexin Huang, Botian Jiang, Zhe Xu, Yiwei Zhao, Min Liang, Shuang Chen, Xipeng Qiu

diffusion efficiency multimodal

Hugging Face Trending Papers

Jun 24

Does Translation-Enhanced Speech Encoder Pre-training Affect Speech LLMs?

Connecting a pre-trained speech encoder to a Large Language Model (LLM) is the standard architecture for building Speech LLMs. However, a structural misalignment exists between the encoder and the LLM.

llms multimodal

arXiv AI

Aug 6

Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders

arXiv:2608. 04586v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).

By Yexing Du, Kaiyuan Liu, Youcheng Pan, Bo Yang, Chengpeng Fu, Yu Wang, Ming Liu

llms multimodal benchmarks safety

Related stories