Thai Semantic End-of-Turn Detection for Real-Time Voice Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914075781365760 |
|---|---|
| author | Popit, Thanapol Rungseesiripak, Natthapath Charattrakool, Monthol Ruangtanusak, Saksorn |
| author_facet | Popit, Thanapol Rungseesiripak, Natthapath Charattrakool, Monthol Ruangtanusak, Saksorn |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04016 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Thai Semantic End-of-Turn Detection for Real-Time Voice Agents Popit, Thanapol Rungseesiripak, Natthapath Charattrakool, Monthol Ruangtanusak, Saksorn Computation and Language Artificial Intelligence 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. |
| title | Thai Semantic End-of-Turn Detection for Real-Time Voice Agents |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.04016 |