# Thai Semantic End-of-Turn Detection for Real-Time Voice Agents

arXiv: https://arxiv.org/abs/2510.04016 · HTML: https://mlsanity.com/paper/2510.04016/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [YODAS: Youtube-Oriented Dataset for Audio and Speech](https://mlsanity.com/paper/2406.00899/) (2024)
- [TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog](https://mlsanity.com/paper/2010.10874/) (2020)
- [WangchanBERTa: Pretraining transformer-based Thai Language Models](https://mlsanity.com/paper/2101.09635/) (2021)
- [Applying General Turn-taking Models to Conversational Human-Robot Interaction](https://mlsanity.com/paper/2501.08946/) (2025)
- [Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models](https://mlsanity.com/paper/2412.13702/) (2024)
- [Improving End-of-turn Detection in Spoken Dialogues by Detecting Speaker Intentions as a Secondary Task](https://mlsanity.com/paper/1805.06511/) (2018)
- [Response-conditioned Turn-taking Prediction](https://mlsanity.com/paper/2305.02036/) (2023)
- [Predictive Speech Recognition and End-of-Utterance Detection Towards Spoken Dialog Systems](https://mlsanity.com/paper/2409.19990/) (2024)
- [Dialogue Response Prefetching Based on Semantic Similarity and Prediction Confidence of Language Model](https://mlsanity.com/paper/2508.04403/) (2025)

## Built on by (most cited first, 2 of 2)

- [TamilEOT: A Dataset and Model for Semantic End-of-Turn Detection in Tamil Telephone Speech](https://mlsanity.com/paper/2609.05631/) (2026)
- [SCB: SpeechConversationBench for Evaluating Multi-Turn Reasoning in Speech-to-Speech Models](https://mlsanity.com/paper/2609.40198/) (2026)

## Abstract (arXiv)

Fluid voice-to-voice interaction requires reliable and low-latency detection of when a user has finished speaking. Traditional audio-silence end-pointers add hundreds of milliseconds of delay and fail under hesitations or language-specific phenomena. We present, to our knowledge, the first systematic study of Thai text-only end-of-turn (EOT) detection for real-time agents. We compare zero-shot and few-shot prompting of compact LLMs to supervised fine-tuning of lightweight transformers. Using transcribed subtitles from the YODAS corpus and Thai-specific linguistic cues (e.g., sentence-final particles), we formulate EOT as a binary decision over token boundaries. We report a clear accuracy-latency tradeoff and provide a public-ready implementation plan. This work establishes a Thai baseline and demonstrates that small, fine-tuned models can deliver near-instant EOT decisions suitable for on-device agents.