← authors · overview

• AutoSpeech: Neural Architecture Search for Speaker Recognition
  2020 · 14 citations
• Personal VAD: Speaker-Conditioned Voice Activity Detection
  2019 · 8 citations
• Textual Echo Cancellation
  2020 · 7 citations
• Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis
  2021 · 2 citations
• RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models
  2023 · 2 citations
• Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition
  2022 · 1 citations
• 4-bit Conformer with Native Quantization Aware Training for Speech Recognition
  2022
• A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
  2022
• Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models
  2023
• 2-bit Conformer quantization for automatic speech recognition
  2023
• USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models
  2023