← authors · overview

• UniCodec: Unified Audio Codec with Single Domain-Adaptive Codebook
  2025 · 2 citations
• Romanization Encoding For Multilingual ASR
  2024 · 1 citations
• Qwen3-ASR Technical Report
  2026
• HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding
  2026
• A Unified and Reproducible Experimentation Framework for Speech Understanding
  2026
• TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs
  2026
• Detect, Attend and Extract: Keyword Guided Target Speaker Extraction
  2026
• TC-BiMamba: Trans-Chunk bidirectionally within BiMamba for unified streaming and non-streaming ASR
  2026
• Time-Layer Adaptive Alignment for Speaker Similarity in Flow-Matching Based Zero-Shot TTS
  2025
• Joint decoding method for controllable contextual speech recognition based on Speech LLM
  2025
• Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning
  2025
• Contrastive Learning With Audio Discrimination For Customizable Keyword Spotting In Continuous Speech
  2024
• TDT-KWS: Fast And Accurate Keyword Spotting Using Token-and-duration Transducer
  2024
• Text-aware Speech Separation for Multi-talker Keyword Spotting
  2024
• Semi-supervised Learning for Code-Switching ASR with Large Language Model Filter
  2024