← authors · overview

• AST: Audio Spectrogram Transformer
  2021 · 989 citations
• An Unsupervised Autoregressive Model for Speech Representation Learning
  2019 · 350 citations
• Frame-level speaker embeddings for text-independent speaker recognition and analysis of end-to-end model
  2018 · 86 citations
• Learning Latent Representations for Speech Generation and Transformation
  2017 · 53 citations
• Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems
  2017 · 48 citations
• Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces
  2018 · 48 citations
• Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech
  2018 · 34 citations
• Towards Transfer Learning for End-to-End Speech Synthesis from Deep Pre-Trained Language Models