research
∙
08/26/2023
How Can Context Help? Exploring Joint Retrieval of Passage and Personalized Context
The integration of external personalized context information into docume...
share
research
∙
02/27/2023
Diagonal State Space Augmented Transformers for Speech Recognition
We improve on the popular conformer architecture by replacing the depthw...
research
∙
06/16/2022
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization
We report on aggressive quantization strategies that greatly accelerate ...
research
∙
03/29/2022
Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing
We introduce two techniques, length perturbation and n-best based label ...
research
∙
10/21/2021
Asynchronous Decentralized Distributed Training of Acoustic Models
Large-scale distributed training of deep acoustic models plays an import...
research
∙
08/27/2021
4-bit Quantization of LSTM-based Speech Recognition Models
We investigate the impact of aggressive low-precision representations of...
research
∙
08/24/2021
Reducing Exposure Bias in Training Recurrent Neural Network Transducers
When recurrent neural network transducers (RNNTs) are trained using the ...
research
∙
06/09/2021
On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation
In the recent advances of natural language processing, the scale of the ...
research
∙
04/21/2021
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
Large-scale distributed training of Deep Neural Networks (DNNs) on state...
research
∙
02/08/2021
Federated Acoustic Modeling For Automatic Speech Recognition
Data privacy and protection is a crucial issue for any automatic speech ...
research
∙
02/03/2021
Speech Emotion Recognition with Multiscale Area Attention and Data Augmentation
In Speech Emotion Recognition (SER), emotional characteristics often app...
research
∙
05/20/2020
Map Generation from Large Scale Incomplete and Inaccurate Data Labels
Accurately and globally mapping human infrastructure is an important and...
research
∙
02/24/2020
Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition
The past decade has witnessed great progress in Automatic Speech Recogni...
research
∙
02/04/2020
Improving Efficiency in Large-Scale Decentralized Distributed Training
Decentralized Parallel SGD (D-PSGD) and its asynchronous variant Asynchr...
research
∙
12/26/2019
Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets
Adaptive gradient algorithms perform gradient-based updates using the hi...
research
∙
10/28/2019
Decentralized Parallel Algorithm for Training Generative Adversarial Nets
Generative Adversarial Networks (GANs) are powerful class of generative ...
research
∙
08/09/2019
Challenging the Boundaries of Speech Recognition: The MALACH Corpus
There has been huge progress in speech recognition over the last several...
research
∙
07/10/2019
Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition
In automatic speech recognition (ASR), wideband (WB) and narrowband (NB)...
research
∙
07/10/2019
Acoustic Model Optimization Based On Evolutionary Stochastic Gradient Descent with Anchors for Automatic Speech Recognition
Evolutionary stochastic gradient descent (ESGD) was proposed as a popula...
research
∙
07/10/2019
A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition
Modern Automatic Speech Recognition (ASR) systems rely on distributed de...
research
∙
04/10/2019
Distributed Deep Learning Strategies For Automatic Speech Recognition
In this paper, we propose and investigate a variety of distributed deep ...
research
∙
10/16/2018
Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks
We propose a population-based Evolutionary Stochastic Gradient Descent (...
research
∙
10/17/2017
Embedding-Based Speaker Adaptive Training of Deep Neural Networks
An embedding-based speaker adaptive training (SAT) approach is proposed ...
research
∙
10/05/2017
Dilated Recurrent Neural Networks
Learning with recurrent neural networks (RNNs) on long sequences is a no...
research
∙
03/06/2017