mlsanityData to 7 Oct 2026

NAVER LABS Europe Submission to the Instruction-following 2026 Short Track

arXiv 2607.01960 ↗First posted 2 Jul 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we describe NAVER LABS Europe's submission to the instruction-following speech processing short track at IWSLT 2026. We participate again in the constrained setting, developing systems capable of jointly performing ASR, ST, and SQA from English speech into Chinese, Italian, and German. Building on our previous submission, ranked first in last year's short track, we update our multi-stage training pipeline by replacing the speech projector with SpeechMapper, a method for learning a speech-to-LLM embedding projector using only ASR data. In addition, we introduce a synthetic SQA dataset, fakACL, composed of artificially generated scientific presentations. This dataset is built by prompting the LLM backbone, segmenting the generated talks, and synthesizing speech with SeamlessM4T-large-v2. The combination of an improved speech projection mechanism and domain-specific synthetic data allows our model to outperform last year's best short-track system, while being considerably more compact and relying on a weaker LLM backbone. This year's results place our system tied for first place in the overall short track ranking.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 28 references that are in the map. First posted on arXiv 2 Jul 2026.

Builds on

17 of 28 references.

References · 17

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 536
  3. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 492
  4. 2025Qwen3-Omni Technical Reportcited by 451
  5. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  6. 2023AudioPaLM: A Large Language Model That Can Speak and Listencited by 333
  7. 2023AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Headcited by 264
  8. 2023SeamlessM4T: Massively Multilingual & Multimodal Machine Translationcited by 124
  9. 2024Spirit LM: Interleaved Spoken and Written Language Modelcited by 123
  10. 2019Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debatescited by 114
  11. 2024EuroLLM: Multilingual Language Models for Europecited by 103
  12. 2020CoVoST 2 and Massively Multilingual Speech-to-Text Translationcited by 73
5 more
  1. 2022GigaST: A 10,000-hour Pseudo Speech Translation Corpuscited by 20
  2. 2025MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talkscited by 14
  3. 2023LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Modelscited by 13
  4. 2025NAVER LABS Europe Submission to the Instruction-following Trackcited by 5
  5. 2026SpeechMapper: Speech-to-text Embedding Projector for LLMscited by 3

Built on by

Not cited yet.