Accurate recognition of specific categories, such as persons' names, dat...
This paper presents a state-of-the-art model for transcribing speech in ...
We introduce the Universal Speech Model (USM), a single large model that...
We propose a novel method to accelerate training and inference process o...
Language identification is critical for many downstream tasks in automat...
On-device end-to-end (E2E) models have shown improvements over a convent...
Building ASR models across many language families is a challenging multi...
Lingvo is a Tensorflow framework offering a complete solution for
collab...
Conventional spoken language understanding systems consist of two main
c...
Current state-of-the-art automatic speech recognition systems are traine...