Exploring RNN-Transducer for Chinese Speech Recognition

11/13/2018
by   Senmao Wang, et al.
0

End-to-end approaches have drawn much attention recently for significantly simplifying the construction of an automatic speech recognition (ASR) system. RNN transducer (RNN-T) is one of the popular end-to-end methods. Previous studies have shown that RNN-T is difficult to train and a very complex training process is needed for a reasonable performance. In this paper, we explore RNN-T for a Chinese large vocabulary continuous speech recognition (LVCSR) task and aim to simplify the training process while maintaining performance. First, a new strategy of learning rate decay is proposed to accelerate the model convergence. Second, we find that adding convolutional layers at the beginning of the network and using ordered data can discard the pre-training process of the encoder without loss of performance. Besides, we design experiments to find a balance among the usage of GPU memory, training circle and model performance. Finally, we achieve 16.9 2 trained on the same text corpus.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/01/2020

Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition

Recently, the recurrent neural network transducer (RNN-T) architecture h...
research
09/26/2019

Improving RNN Transducer Modeling for End-to-End Speech Recognition

In the last few years, an emerging trend in automatic speech recognition...
research
07/30/2020

Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability

Because of its streaming nature, recurrent neural network transducer (RN...
research
02/03/2021

Effects of Number of Filters of Convolutional Layers on Speech Recognition Model Accuracy

Inspired by the progress of the End-to-End approach [1], this paper syst...
research
11/29/2022

Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation

The neural transducer is an end-to-end model for automatic speech recogn...
research
03/31/2022

Memory-Efficient Training of RNN-Transducer with Sampled Softmax

RNN-Transducer has been one of promising architectures for end-to-end au...
research
04/27/2021

On Addressing Practical Challenges for RNN-Transducer

In this paper, several works are proposed to address practical challenge...

Please sign up or login with your details

Forgot password? Click here to reset