Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion

arXiv:2609.14991 · cs.CL, cs.SD, eess.AS · Submitted 2026-09-14 · Read on arXiv

cs.CL, cs.SD, eess.AS

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 4 pages, 2 figures, 3 tables. Accepted to IEEE SLT 2026 (Demo Track)

Project page: https://warit-s.github.io/typhoon-asr-streaming

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 6× in this paper · explained in 1 episode
• Decode — 6× in this paper · explained in 2 episodes
• Steering — 6× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Automatic Speech Recognition (ASR) — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• International Conference on Machine Learning — 1× in this paper
• Low-Resource Languages — 1× in this paper · explained in 4 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition
• On Using Monolingual Corpora in Neural Machine Translation
• NeMo: a toolkit for building AI applications using Neural Modules

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering