← authors · overview

• Unsupervised Learning of Semantic Audio Representations
  2017 · 5 citations
• Unsupervised word segmentation and lexicon discovery using acoustic word embeddings
  2016
• A segmental framework for fully-unsupervised large-vocabulary speech recognition
  2016
• Improving Universal Sound Separation Using Sound Classification
  2019
• Towards Learning a Universal Non-Semantic Representation of Speech
  2020
• BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
  2021
• Universal Paralinguistic Speech Representations Using Self-Supervised Conformers
  2021
• Text-Driven Separation of Arbitrary Sounds
  2022
• Long-Form Speech Generation with Spoken Language Models
  2024