activity
20162022
most citedLingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

184 citations · 193 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

9 papers · 1 filter

cs.CL2022

Handling Compounding in Mobile Keyboard Input

Andreas Kabel, Keith Hall, Tom Ouyang +3

This paper proposes a framework to improve the typing experience of mobile users in morphologically rich languages. Smartphone keyboards typically support features such as input de…

cs.CL2021

Lookup-Table Recurrent Language Models for Long Tail Speech Recognition

W. Ronny Huang, Tara N. Sainath, Cal Peyser +3

We introduce Lookup-Table Language Models (LookupLM), a method for scaling up the size of RNN language models with only a constant increase in the floating point operations, by inc…

cs.CL2020

Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging

Rohit Prabhavalkar, Yanzhang He, David Rybach +4

End-to-end models that condition the output label sequence on all previously predicted labels have emerged as popular alternatives to conventional systems for automatic speech reco…

cs.CL20203 cited

A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency

Tara N. Sainath, Yanzhang He, Bo Li +26

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e…

cs.CL2019

Two-Pass End-to-End Speech Recognition

Tara N. Sainath, Ruoming Pang, David Rybach +9

The requirements for many applications of state-of-the-art speech recognition systems include not only low word error rate (WER) but also low latency. Specifically, for many use-ca…

cs.CL2019

On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition

Kazuki Irie, Rohit Prabhavalkar, Anjuli Kannan +3

In conventional speech recognition, phoneme-based models outperform grapheme-based models for non-phonetic languages such as English. The performance gap between the two typically…