Metraipolis › archive › dc_d9ed368dcfa3
Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion — arXiv:2609.14991
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14991
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T23:15:42.624Z
- SHA-256 of the archived text
756f88804fa6a9f87e2386d5d681b9b998d687d7116f60b0e723fd5a27a78ef0- Stable URL of this page
https://metraipolis.com/documento/dc_d9ed368dcfa3
How to cite
Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion — arXiv:2609.14991 — arXiv (en), https://arxiv.org/abs/2609.14991 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d9ed368dcfa3 (Metraipolis archive dc_d9ed368dcfa3, sha256 756f88804fa6a9f87e2386d5d681b9b998d687d7116f60b0e723fd5a27a78ef0)
BibTeX
@misc{dcd9ed368dcfa3,
title = {Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion — arXiv:2609.14991},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14991},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d9ed368dcfa3; sha256 756f88804fa6a9f87e2386d5d681b9b998d687d7116f60b0e723fd5a27a78ef0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14991. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling out low-latency uses such as live captioning and voice agents. We present a deployable system for streaming Thai ASR that lets a user steer its vocabulary at decode time, without retraining. A widely used open Thai model, trained with full context, collapses when run as a true stream; we restore streaming with a cache-aware encoder, by converting it or adapting a natively streaming one, and add a shallow-fusion layer that re-ranks candidates inside the streaming decoder with a GPU n-gram language model and phrase boosting. Across two Thai benchmarks and two model sizes, the streaming models stay usable where the full-context model fails, cutting character error rate 4.3-4.5x at a one-second look-ahead while running faster than real time. Decode-time steering then lifts keyword recall from 16.6% to 20.7% at no accuracy cost and negligible overhead; most of the gain comes from an n-gram over ordinary training transcripts, which resolves the written form of code-switched words the model hears but spells inconsistently, with phrase boosting adding targeted control over rare domain terms. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Sound (cs.SD); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2609.14991 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T22:51:09.921Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).