We introduce LAST, a LAttice-based Speech Transducer library in JAX. Wit...
We propose JEIT, a joint end-to-end (E2E) model and internal language mo...
Existing training criteria in automatic speech recognition(ASR) permit t...
Text-only adaptation of a transducer model remains challenging for end-t...
Personalization of speech models on mobile devices (on-device
personaliz...
We introduce the Globally Normalized Autoregressive Transducer (GNAT) fo...
Language models (LMs) significantly improve the recognition accuracy of
...
End-to-end (E2E) automatic speech recognition (ASR) models, by now, have...
This paper proposes and evaluates the hybrid autoregressive transducer (...
This article describes a density ratio approach to integrating external
...
Most of the parameters in large vocabulary models are used in embedding ...
In this paper, we describe how to efficiently implement an acoustic room...
The problem of target localization with noise is addressed. The target i...