20 citations · 26 across the 8 of their papers we have counts for
8 papers
Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition
Maurits Bleeker, Pawel Swietojanski, Stefan Braun +1
This paper presents an extension to train end-to-end Context-Aware Transformer Transducer ( CATT ) models by using a simple, yet efficient method of mining hard negative phrases fr…
Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation
Stefan Braun, Erik McDermott, Roger Hsiao
The neural transducer is an end-to-end model for automatic speech recognition (ASR). While the model is well-suited for streaming ASR, the training process remains challenging. Dur…
Variable Attention Masking for Configurable Transformer Transducer Speech Recognition
Pawel Swietojanski, Stefan Braun, Dogan Can +9
This work studies the use of attention masking in transformer transducer based speech recognition for building a single configurable model for different deployment scenarios. We pr…
Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation
Thien Nguyen, Nathalie Tran, Liuhui Deng +16
Code-switching describes the practice of using more than one language in the same sentence. In this study, we investigate how to optimize a neural transducer based bilingual automa…
SapAugment: Learning A Sample Adaptive Policy for Data Augmentation
Ting-Yao Hu, Ashish Shrivastava, Jen-Hao Rick Chang +5
Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a N…
LSTM Benchmarks for Deep Learning Frameworks
Stefan Braun
This study provides benchmarks for different implementations of LSTM units between the deep learning frameworks PyTorch, TensorFlow, Lasagne and Keras. The comparison includes cuDN…
Sensor Transformation Attention Networks
Stefan Braun, Daniel Neil, Enea Ceolini +2
Recent work on encoder-decoder models for sequence-to-sequence mapping has shown that integrating both temporal and spatial attention mechanisms into neural networks increases the…
A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition
Stefan Braun, Daniel Neil, Shih-Chii Liu
The performance of automatic speech recognition systems under noisy environments still leaves room for improvement. Speech enhancement or feature enhancement techniques for increas…