← authors · overview

• Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
  2023 · 2 citations
• Memory-efficient Speech Recognition on Smart Devices
  2021 · 1 citations
• Noisy Training Improves E2E ASR for the Edge
  2021 · 1 citations
• Exploring Speech Enhancement for Low-resource Speech Synthesis
  2023 · 1 citations
• High Fidelity Text-Guided Music Editing via Single-Stage Flow Matching
  2024 · 1 citations
• Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions
  2024
• Collaborative Training of Acoustic Encoders for Speech Recognition
  2021
• Streaming parallel transducer beam search with fast-slow cascaded encoders
  2022
• TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
  2023
• Enhance audio generation controllability through representation similarity regularization
  2023
• Stack-and-Delay: a new codebook pattern for music generation
  2023
• On The Open Prompt Challenge In Conditional Audio Generation
  2023