Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription
cs.CL, cs.AI, cs.SD
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/netease-youdao/Confucius4-R2T2
Terminology
Sources
- Accelerating Large Language Model Decoding with Speculative Sampling
- Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent
- Monotonic Chunkwise Attention
- Earnings-22: A Practical Benchmark for Accents in the Wild
- Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation
- Dynamic Lagging using Stable-Prefix Training for Simultaneous Translation
- Voxtral Realtime
- Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Qwen3-ASR Technical Report
- Factorized Delayed Streams Modeling for LLM-based Streaming ASR
- Streaming Speech Recognition with Decoder-Only Large Language Models and Latency Optimization
- U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition
- Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling
- Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition
- Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data