paper-with-me

홈 › Papers

FBK's Long-form SpeechLLMs for IWSLT 2026 Instruction Following

2026-06-25 · Zhihang Xie, Marco Gaido, Sara Papi, Matteo Negri, Luisa Bentivogli arxiv

This paper describes our submission to the IWSLT 2026 Instruction Following shared task. SpeechLLMs are developed for both short-form and long-form speech instruction following under constrained settings. For the short track, strong performance is achieved on MCIF, with a SIFS score of 2.0708. For the long track, three speech segmentation methods are explored, and the HIFS score is introduced to account for unstable long-form generation. Experimental results show that fixed 30-second segmentation provides the most robust long-form performance, achieving the highest HIFS score of 2.0663. Further analysis shows that hallucination mainly manifests as repetitive insertions in generated outputs, substantially affecting ASR and SSUM, while short-form capabilities are largely retained after long-form extension.

📄 PDF Abstract BibTeX arXiv:2606.26819

Code (0)

등록된 구현이 없습니다.

Tasks

Instruction Following

Similar Papers 제목 키워드 기반

Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026

2026-06-03 · Enes Yavuz Ugan, Maike Züfle, Yuka Ko, Supriti Sinhamahapatra 외 arxiv

With the advent of Large Language Models, single-task and token-based multi-task models have evolved into instruction-based systems that infer task and target language implicitly from natural language prompts. This trend…

Instruction FollowingData Augmentation

NAVER LABS System Re-implementation for the IWSLT 2026 Instruction-Following Task

2026-07-06 · Anand Kamble, Aniket Tathe arxiv

We re-implement the NAVER LABS IWSLT 2025 instruction-following pipeline for the IWSLT 2026 Shared Task (constrained condition, short audio track), adapting it to the mandated components: SeamlessM4T-v2-large as the spee…

SpeechLLMs for Large-scale Contextualized Zero-shot Slot Filling

2025-10-17 · Kadri Hacioglu, Manjunath K E, Andreas Stolcke arxiv

Slot filling is a crucial subtask in spoken language understanding (SLU), traditionally implemented as a cascade of speech recognition followed by one or more natural language understanding (NLU) components. The recent a…

Natural Language UnderstandingSpoken Language UnderstandingZero-shot Slot FillingSpeech Recognition

KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025

2025-05-19 · Sai Koneru, Maike Züfle, Thai-Binh Nguyen, Seymanur Aktı 외

The scope of the International Workshop on Spoken Language Translation (IWSLT) has recently broadened beyond traditional Speech Translation (ST) to encompass a wider array of tasks, including Speech Question Answering an…

Automatic Speech RecognitionInstruction FollowingQuestion Answeringspeech-recognition+2

InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training

2025-03-04 · Dingdong Wang, Jin Xu, Ruihang Chu, Zhifang Guo 외

Recent advancements in speech large language models (SpeechLLMs) have attracted considerable attention. Nonetheless, current methods exhibit suboptimal performance in adhering to speech instructions. Notably, the intelli…

Instruction Followingtext-to-speechText to Speech