all AI news
Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator. (arXiv:2205.09058v1 [cs.CL])
May 19, 2022, 1:11 a.m. | Guangzhi Sun, Chao Zhang, Philip C Woodland
cs.CL updates on arXiv.org arxiv.org
Contextual knowledge is essential for reducing speech recognition errors on
high-valued long-tail words. This paper proposes a novel tree-constrained
pointer generator (TCPGen) component that enables end-to-end ASR models to bias
towards a list of long-tail words obtained using external contextual
information. With only a small overhead in memory use and computation cost,
TCPGen can structure thousands of biasing words efficiently into a symbolic
prefix-tree and creates a neural shortcut between the tree and the final ASR
output to facilitate the …
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Data Engineer
@ Chubb | Simsbury, CT, United States
Research Analyst , NA Light Vehicle Powertrain Forecasting
@ S&P Global | US - MI - VIRTUAL
Sr. Data Scientist - ML Ops Job
@ Yash Technologies | Indore, IN
Alternance-Data Management
@ Keolis | Courbevoie, FR, 92400