← authors · overview

• SUPERB: Speech processing Universal PERformance Benchmark
  2021 · 51 citations
• Towards Robust Neural Vocoding for Speech Generation: A Survey
  2019 · 23 citations
• Understanding Self-Attention of Self-Supervised Audio Transformers
  2020 · 4 citations
• Don't speak too fast: The impact of data bias on self-supervised speech models
  2021 · 3 citations
• SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities
  2022 · 3 citations
• MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues
  2024 · 2 citations
• A Large-Scale Evaluation of Speech Foundation Models
  2024 · 1 citations
• ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction
  2025
• Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget
  2024
• Parallel Synthesis for Autoregressive Speech Generation
  2022
• Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
  2024
• Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling
  2024