← Search

Brian John King

2 accepted papers

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…

Cited by 9SourcePDFScholar
2021

End-to-End Multi-Channel Transformer for Speech Recognition

ICASSP 2021accepted

Transformers are powerful neural architectures that allow integrating different modalities using attention mechanisms. In this paper, we leverage the neural transformer architectures for multi-channel speech recognition systems, where the spectral and spatial information collected from different mic…

Cited by 0SourceScholar