[PDF][PDF] Recent advances in end-to-end automatic speech recognition

J Li - APSIPA Transactions on Signal and Information …, 2022 - nowpublishers.com
Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

The speech neuroprosthesis

AB Silva, KT Littlejohn, JR Liu, DA Moses… - Nature Reviews …, 2024 - nature.com
Loss of speech after paralysis is devastating, but circumventing motor-pathway injury by
directly decoding speech from intact cortical activity has the potential to restore natural …

Google usm: Scaling automatic speech recognition beyond 100 languages

Y Zhang, W Han, J Qin, Y Wang, A Bapna… - ar** real-time streaming transformer transducer for speech recognition on large-scale dataset
X Chen, Y Wu, Z Wang, S Liu… - ICASSP 2021-2021 IEEE …, 2021 - ieeexplore.ieee.org
Recently, Transformer based end-to-end models have achieved great success in many
areas including speech recognition. However, compared to LSTM models, the heavy …

Recent progress in transformer-based medical image analysis

Z Liu, Q Lv, Z Yang, Y Li, CH Lee, L Shen - Computers in Biology and …, 2023 - Elsevier
The transformer is primarily used in the field of natural language processing. Recently, it has
been adopted and shows promise in the computer vision (CV) field. Medical image analysis …

Parp: Prune, adjust and re-prune for self-supervised speech recognition

CIJ Lai, Y Zhang, AH Liu, S Chang… - Advances in …, 2021 - proceedings.neurips.cc
Self-supervised speech representation learning (speech SSL) has demonstrated the benefit
of scale in learning rich representations for Automatic Speech Recognition (ASR) with …

Contextualized streaming end-to-end speech recognition with trie-based deep biasing and shallow fusion

D Le, M Jain, G Keren, S Kim, Y Shi… - arxiv preprint arxiv …, 2021 - arxiv.org
How to leverage dynamic contextual information in end-to-end speech recognition has
remained an active research area. Previous solutions to this problem were either designed …

Xrbench: An extended reality (xr) machine learning benchmark suite for the metaverse

H Kwon, K Nair, J Seo, J Yik… - Proceedings of …, 2023 - proceedings.mlsys.org
Real-time multi-task multi-model (MTMM) workloads, a new form of deep learning inference
workloads, are emerging for applications areas like extended reality (XR) to support …