Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation

no code implementations • 2 Jun 2023 • Hanbyul Kim, Seunghyun Seo, Lukas Lee, Seolki Baek

Punctuated text prediction is crucial for automatic speech recognition as it enhances readability and impacts downstream natural language processing tasks.

Automatic Speech Recognition speech-recognition +1

Better Intermediates Improve CTC Inference

no code implementations • 1 Apr 2022 • Tatsuya Komatsu, Yusuke Fujita, Jaesong Lee, Lukas Lee, Shinji Watanabe, Yusuke Kida

This paper proposes a method for improved CTC inference with searched intermediates and multi-pass conditioning.

Memory-Efficient Training of RNN-Transducer with Sampled Softmax

no code implementations • 31 Mar 2022 • Jaesong Lee, Lukas Lee, Shinji Watanabe

RNN-Transducer has been one of promising architectures for end-to-end automatic speech recognition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

EXPLORATION OF EFFICIENT ON-DEVICE ACOUSTIC MODELING WITH NEURAL NETWORKS

no code implementations • 27 Sep 2018 • Wonyong Sung, Lukas Lee, Jinwhan Park

In addition, we explore neural networks that equip one-dimensional (1-D) convolution at each layer of these algorithms, and by which can obtain a very large performance increase in the QRNNs and Gated ConvNets.

speech-recognition Speech Recognition