[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 …

[HTML][HTML] Progress in machine translation

H Wang, H Wu, Z He, L Huang, KW Church - Engineering, 2022 - Elsevier
After more than 70 years of evolution, great achievements have been made in machine
translation. Especially in recent years, translation quality has been greatly improved with the …

End-to-end speech recognition: A survey

R Prabhavalkar, T Hori, TN Sainath… - … on Audio, Speech …, 2023 - ieeexplore.ieee.org
In the last decade of automatic speech recognition (ASR) research, the introduction of deep
learning has brought considerable reductions in word error rate of more than 50% relative …

Seamless: Multilingual Expressive and Streaming Speech Translation

L Barrault, YA Chung, MC Meglioli, D Dale… - ar**, converting images to a top-down view of the world, as
a translation problem. We show how a novel form of transformer network can be used to …

Fairseq S2T: Fast speech-to-text modeling with fairseq

C Wang, Y Tang, X Ma, A Wu, S Popuri… - ar** artificial learning systems that can understand and generate natural language
has been one of the long-standing goals of artificial intelligence. Recent decades have …

Monotonic multihead attention

X Ma, J Pino, J Cross, L Puzon, J Gu - arxiv preprint arxiv:1909.12406, 2019 - arxiv.org
Simultaneous machine translation models start generating a target sequence before they
have encoded or read the source sequence. Recent approaches for this task either apply a …

Dual-mode ASR: Unify and improve streaming ASR with full-context modeling

J Yu, W Han, A Gulati, CC Chiu, B Li… - arxiv preprint arxiv …, 2020 - arxiv.org
Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as
quickly and accurately as possible, while full-context ASR waits for the completion of a full …

SimulMT to SimulST: Adapting simultaneous text translation to end-to-end simultaneous speech translation

X Ma, J Pino, P Koehn - arxiv preprint arxiv:2011.02048, 2020 - arxiv.org
Simultaneous text translation and end-to-end speech translation have recently made great
progress but little work has combined these tasks together. We investigate how to adapt …