7 papers and 1 tutorial are accepted to Interspeech 23

  • Tutorial Video: Resource-Efficient and Cross-Modal Learning Toward Foundation Models

  • Papers, where Speech Reprogramming has been nominated for best student paper candidates; also see Hao’s video here.

  1. How to Estimate Model Transferability of Pre-Trained Speech Models? (Code)

  2. Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Classification (Code)

  3. Parameter-Efficient Learning for Text-to-Speech Accent Adaptation (Code)

  4. Differentially Private Adapters for Parameter Efficient Acoustic Modeling (Code)

  5. A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models (Code)

  6. A Neural State-Space Model Approach to Efficient Speech Separation

  7. A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Model (Code)