research
∙
04/25/2023
LAST: Scalable Lattice-Based Speech Modelling in JAX
We introduce LAST, a LAttice-based Speech Transducer library in JAX. Wit...
share
research
∙
02/16/2023
JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition
We propose JEIT, a joint end-to-end (E2E) model and internal language mo...
research
∙
12/22/2022
Alignment Entropy Regularization
Existing training criteria in automatic speech recognition(ASR) permit t...
research
∙
10/31/2022
Modular Hybrid Autoregressive Transducer
Text-only adaptation of a transducer model remains challenging for end-t...
research
∙
07/02/2022
UserLibri: A Dataset for ASR Personalization Using Only Text
Personalization of speech models on mobile devices (on-device personaliz...
research
∙
05/26/2022
Global Normalization for Streaming Speech Recognition in a Modular Framework
We introduce the Globally Normalized Autoregressive Transducer (GNAT) fo...
research
∙
04/15/2022
Improving Rare Word Recognition with LM-aware MWER Training
Language models (LMs) significantly improve the recognition accuracy of ...
research
∙
10/27/2020
Cascaded encoders for unifying streaming and non-streaming ASR
End-to-end (E2E) automatic speech recognition (ASR) models, by now, have...
research
∙
03/12/2020
Hybrid Autoregressive Transducer (hat)
This paper proposes and evaluates the hybrid autoregressive transducer (...
research
∙
02/26/2020
A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition
This article describes a density ratio approach to integrating external ...
research
∙
11/20/2018
WEST: Word Encoded Sequence Transducers
Most of the parameters in large vocabulary models are used in embedding ...
research
∙
12/09/2017
Efficient Implementation of the Room Simulator for Training Deep Neural Network Acoustic Models
In this paper, we describe how to efficiently implement an acoustic room...
research
∙
04/22/2015