Hugo Van hamme

Papers

Total Citations

H-Index

About

Hugo Van hamme is a leading researcher in speech processing and machine learning, with a focus on enabling machines to acquire language through interaction rather than pre-programmed linguistic knowledge. His key research areas include cognitive robotics, human-machine interfaces, and assistive technologies, where he pioneers methods for unsupervised and weakly supervised learning of speech. Van hamme’s major contributions center on using non-negative matrix factorization (NMF) to allow robots and devices to learn word models directly from spoken examples, bypassing traditional linguistic priors. His 2014 paper on “Acquisition of ordinal words using weakly supervised NMF” (14 citations) demonstrates a vocal interface that learns through demonstration, while his 2012 work on “Fast word acquisition in an NMF-based learning framework” (10 citations) shows how systems can autonomously build small vocabularies from usage. Though citation counts are modest, these works have been influential in advancing adaptive speech recognition for assistive devices and cognitive robotics. Van hamme’s research stands out for its practical, user-centered approach, making speech interfaces more accessible and intuitive for individuals with communication challenges.