2023
Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers
ICML 2023poster
Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures emit tokens at each frame, relying only on current and past signal, while non-causal models are exposed to a window of…