-
BDF6 SAV schemes for time-fractional Allen-Cahn dissipative systems
Recently, the error analysis of BDFk (1⩽ k⩽5) SAV (scalar auxiliary vari...
04/19/2021 ∙ by Fan Yu, et al. ∙
0
∙
share
read it
-
Boundary and Context Aware Training for CIF-based Non-Autoregressive End-to-end ASR
Continuous integrate-and-fire (CIF) based models, which use a soft and m...
04/10/2021 ∙ by Fan Yu, et al. ∙
0
∙
share
read it
-
The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods
The variety of accents has posed a big challenge to speech recognition. ...
02/20/2021 ∙ by Xian Shi, et al. ∙
0
∙
share
read it
-
WeNet: Production First and Production Ready End-to-End Speech Recognition Toolkit
In this paper, we present a new open source, production first and produc...
02/02/2021 ∙ by BinBin Zhang, et al. ∙
0
∙
share
read it
-
AsymptoticNG: A regularized natural gradient optimization algorithm with look-ahead strategy
Optimizers that further adjust the scale of gradient, such as Adam, Natu...
12/24/2020 ∙ by Zedong Tang, et al. ∙
9
∙
share
read it
-
Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition
In this paper, we present a novel two-pass approach to unify streaming a...
12/10/2020 ∙ by BinBin Zhang, et al. ∙
0
∙
share
read it
-
Eigenvalue-corrected Natural Gradient Based on a New Approximation
Using second-order optimization methods for training deep neural network...
11/27/2020 ∙ by Kai-Xin Gao, et al. ∙
0
∙
share
read it
-
A Trace-restricted Kronecker-Factored Approximation to Natural Gradient
Second-order optimization methods have the ability to accelerate converg...
11/21/2020 ∙ by Kai-Xin Gao, et al. ∙
0
∙
share
read it
-
The SLT 2021 children speech recognition challenge: Open datasets, rules and baselines
Automatic speech recognition (ASR) has been significantly advanced with ...
11/13/2020 ∙ by Fan Yu, et al. ∙
0
∙
share
read it
-
Backward difference formula: The energy technique for subdiffusion equation
Based on the equivalence of A-stability and G-stability, the energy tech...
10/25/2020 ∙ by Minghua Chen, et al. ∙
0
∙
share
read it
-
The energy technique for the six-step BDF method
In combination with the Grenander–Szegö theorem, we observe that a relax...
07/17/2020 ∙ by Georgios Akrivis, et al. ∙
0
∙
share
read it
-
TensorOpt: Exploring the Tradeoffs in Distributed DNN Training with Auto-Parallelism
A good parallelization strategy can significantly improve the efficiency...
04/16/2020 ∙ by Zhenkun Cai, et al. ∙
8
∙
share
read it
