B
Bernard Merialdo
Researcher at Institut Eurécom
Publications - 127
Citations - 2672
Bernard Merialdo is an academic researcher from Institut Eurécom. The author has contributed to research in topics: TRECVID & Automatic summarization. The author has an hindex of 25, co-authored 127 publications receiving 2604 citations. Previous affiliations of Bernard Merialdo include Joanneum Research & IBM.
Papers
More filters
Journal Article
Tagging English text with a probabilistic model
TL;DR: Experminents show that the best training is obtained by using as much tagged text as possible, and show that Maximum Likelihood training, the procedure that is routinely used to estimate hidden Markov models parameters from training data, will not necessarily improve the tagging accuracy.
Proceedings ArticleDOI
A dynamic language model for speech recognition
TL;DR: The authors proposed a cache trigram language model (CTLM) based on the trigram frequencies estimated from the partially dictated document, which caching the recent history of words to improve the language model.
Proceedings ArticleDOI
Automatic construction of personalized TV news programs
TL;DR: This paper combines video indexing techniques to parse TV News recordings into stories, and information filtering techniques to select stories which are most adequate given the user profile, and formalizes the selection process as an optimization problem.
Journal ArticleDOI
Natural Language Modeling for Phoneme-to-Text Transcription
TL;DR: This paper relates different kinds of language modeling methods that can be applied to the linguistic decoding part of a speech recognition system with a very large vocabulary and proposes a model which combines the advantages of a statistical modeling with information theoretic tools, and those of a grammatical approach.
Proceedings Article
Multi-video summarization based on Video-MMR
Yingbo Li,Bernard Merialdo +1 more
TL;DR: This paper presents a novel and effective approach for multi-video summarization: Video-MMR, which extends a classical algorithm of text summarization, Maximal Marginal Relevance, and compares it with popular K-means algorithm, supported by user-made summary.