Cindy Tseng

Transducer Consistency Regularization For Speech to Text Applications

2024

Consistency regularization is a commonly used practice to encourage the model to generate consistent representation from distorted input features and improve model generalization. It shows significant improvement on various speech applications that are optimized with …

Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization

2025 · arXiv (Cornell University)

Low latency speech human-machine communication is becoming increasingly necessary as speech technology advances quickly in the last decade. One of the primary factors behind the advancement of speech technology is self-supervised learning. Most self-supervised learning …