# Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization

arXiv: https://arxiv.org/abs/2508.08550 · HTML: https://mlsanity.com/paper/2508.08550/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 39 of its 64 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [Secrets of RLHF in Large Language Models Part I: PPO](https://mlsanity.com/paper/2307.04964/) (2023)
- [Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO](https://mlsanity.com/paper/2005.12729/) (2020)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Interactive Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1701.06049/) (2017)
- [Correcting Length Bias in Neural Machine Translation](https://mlsanity.com/paper/1808.10006/) (2018)
- [Controlling Output Length in Neural Encoder-Decoders](https://mlsanity.com/paper/1609.09552/) (2016)
- [Controllable Text Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2408.12599/) (2024)
- [Positional Encoding to Control Output Sequence Length](https://mlsanity.com/paper/1904.07418/) (2019)
- [Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR)](https://mlsanity.com/paper/2001.00139/) (2020)
- [Semi-Supervised Learning for Neural Machine Translation](https://mlsanity.com/paper/1606.04596/) (2016)
- [Controlling the Output Length of Neural Machine Translation](https://mlsanity.com/paper/1910.10408/) (2019)
- [SDPO: Segment-Level Direct Preference Optimization for Social Agents](https://mlsanity.com/paper/2501.01821/) (2025)

## Built on by (most cited first, 3 of 3)

- [JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion](https://mlsanity.com/paper/2601.22143/) (2026)
- [Hermes the Polyglot: A Unified Framework to Enhance Expressiveness for Multimodal Interlingual Subtitling](https://mlsanity.com/paper/2602.00597/) (2026)
- [CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization](https://mlsanity.com/paper/2603.16966/) (2026)

## Abstract (arXiv)

Video dubbing aims to translate original speech in visual media programs from the source language to the target language, relying on neural machine translation and text-to-speech technologies. Due to varying information densities across languages, target speech often mismatches the source speech duration, causing audio-video synchronization issues that significantly impact viewer experience. In this study, we approach duration alignment in LLM-based video dubbing machine translation as a preference optimization problem. We propose the Segment Supervised Preference Optimization (SSPO) method, which employs a segment-wise sampling strategy and fine-grained loss to mitigate duration mismatches between source and target lines. Experimental results demonstrate that SSPO achieves superior performance in duration alignment tasks.