Chengjian Zheng — accepted AI-conference papers

2024

Massive End-to-end Speech Recognition Models with Time Reduction

Weiran Wang, Rohit Prabhavalkar, Haozhe Shan, Zhong Meng, Dongseong Hwang, Qiujia Li +9

NAACL 2024long

We investigate massive end-to-end automatic speech recognition (ASR) models with efficiency improvements achieved by time reduction. The encoders of our models use the neural architecture of Google’s universal speech model (USM), with additional funnel pooling layers to significantly reduce the fram…

Cited by 2 Source ↗PDF ↗Scholar ↗

2023

Accelerating RNN-T Training and Inference Using CTC Guidance

Yongqiang Wang, Zhehuai Chen, Chengjian Zheng, Yu Zhang, Wei Han, Parisa Haghani

ICASSP 2023accepted

We propose a novel method to accelerate training and inference process of recurrent neural network transducer (RNN-T) based on the guidance from a co-trained connectionist temporal classification (CTC) model. We made a key assumption that if an encoder embedding frame is classified as a blank frame…

Cited by 0 Source ↗Scholar ↗