research
∙
03/14/2023
I3D: Transformer architectures with input-dependent dynamic depth for speech recognition
Transformer-based end-to-end speech recognition has achieved great succe...
share
research
∙
10/20/2022
Large-scale learning of generalised representations for speaker recognition
The objective of this work is to develop a speaker recognition model to ...
research
∙
04/01/2022
Better Intermediates Improve CTC Inference
This paper proposes a method for improved CTC inference with searched in...
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
∙
10/11/2021
A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation
Non-autoregressive (NAR) models simultaneously generate multiple outputs...
research
∙
06/17/2021
Layer Pruning on Demand with Intermediate CTC
Deploying an end-to-end automatic speech recognition (ASR) model on mobi...
research
∙
02/05/2021