Signals 4 · free daily AI digest

Transcribe, Translate, and Optimize: Joint Reward Learning for Speech Translation

Paper recorded by Signals 4 on 2026-09-22 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-22 on arXiv · recorded by Signals 4 on 2026-09-23

Category: cs.CL · 自然语言处理 · first seen 2026-09-23

Abstract

In LLM-based speech translation, transcription-based chain-of-thought (CoT) suffers from a mismatch between reference transcripts used in supervised fine-tuning (SFT) and model-generated transcripts at inference. To address this, we propose joint recognition and translation fine-tuning via group relative policy optimization (GRPO). We score both transcripts and translations, with translation condi

Read on arXiv →

#10 most recent of 227 cs.CL papers we have recorded · ↑ newer: A retrospective analysis on the use of LLMs to study infant syntax lea · ↓ older: A Semiotics-Aware Framework for Evaluating Fidelity and Coverage in Na
Cite this page: Transcribe, Translate, and Optimize: Joint Reward Learning for Speech Translation: the #10 most recent of 227 cs.CL papers we have recorded (as of 2026-09-22). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/transcribe-translate-and-optimize-joint-reward-learning-for-speech-translation.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions