3 papers
cs.CL2024
Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR
Zelin Wu, Gan Song, Christopher Li +9
Contextual biasing enables speech recognizers to transcribe important phrases in the speaker's context, such as contact names, even if they are rare in, or absent from, the trainin…
cs.CL2024
High-precision Voice Search Query Correction via Retrievable Speech-text Embedings
Christopher Li, Gary Wang, Kyle Kastner +9
Automatic speech recognition (ASR) systems can suffer from poor recall for various reasons, such as noisy audio, lack of sufficient training data, etc. Previous work has shown that…
physics.soc-ph2023
Response to the paper: Theoretical understanding of evolutionary dynamics on inhomogeneous networks
Christopher Li
As a co-author of the paper Theoretical understanding of evolutionary dynamics on inhomogeneous networks, I would like to express my disagreement with the conclusion of the paper.…