In this work, we study the impact of Large-scale Language Models (LLM) o...
Existing training criteria in automatic speech recognition(ASR) permit t...
We explore unifying a neural segmenter with two-pass cascaded encoder AS...
We introduce the Globally Normalized Autoregressive Transducer (GNAT) fo...
Improving the performance of end-to-end ASR models on long utterances ra...
Language models (LMs) significantly improve the recognition accuracy of
...
This paper proposes a framework to improve the typing experience of mobi...
We introduce Lookup-Table Language Models (LookupLM), a method for scali...
End-to-end models that condition the output label sequence on all previo...
Thus far, end-to-end (E2E) models have not been shown to outperform
stat...
This paper proposes and evaluates the hybrid autoregressive transducer (...
All-neural end-to-end (E2E) automatic speech recognition (ASR) systems t...
The requirements for many applications of state-of-the-art speech recogn...
Lingvo is a Tensorflow framework offering a complete solution for
collab...
We evaluate attention-based encoder-decoder models along two dimensions:...
End-to-end (E2E) models, which directly predict output character sequenc...
For decades, context-dependent phonemes have been the dominant sub-word ...
We propose a finite-state transducer (FST) representation for the models...
We describe a large vocabulary speech recognition system that is accurat...