← Search

Pavel Kveton

2 accepted papers

2022

Caching Networks: Capitalizing on Common Speech for ASR

ICASSP 2022accepted

We introduce Caching Networks (CachingNets), a speech recognition network architecture capable of delivering faster, more accurate decoding by leveraging common speech patterns. By explicitly incorporating select sentences unique to each user into the network’s design, we show how to train the model…

Cited by 0SourceScholar
2022

TINYS2I: A Small-Footprint Utterance Classification Model with Contextual Support for On-Device SLU

ICASSP 2022accepted

On-device spoken language understanding (SLU) offers the potential for significant latency savings compared to cloud-based processing, as the audio stream does not need to be transmitted to a server. We present Tiny Signal-to-interpretation (TinyS2I), an end-to-end on-device SLU approach which is fo…

Cited by 0SourceScholar