Isabel Trancoso
Instituto Superior Técnico
307 Papers
3K Citations
Isabel Trancoso is an academic researcher from Instituto Superior Técnico. The author has contributed to research in topics: European Portuguese & Computer science. The author has an hindex of 33, co-authored 293 publications. Previous affiliations of Isabel Trancoso include INESC-ID & Carnegie Mellon University.
Chat about Author
Papers
•Posted Content
Automatic Fado Music Classification
TL;DR: Frequency spectrum-related characteristics were captured form the audio signal and in addition to the Mel Frequency Cepstral Coefficients (MFCCs) and the energy of the signal, the signal was further analysed in two frequency ranges, providing additional information.
Attacking a privacy preserving music matching algorithm
Jose Portelo,Bhiksha Raj,Isabel Trancoso +2 more
- 25 Mar 2012
TL;DR: This paper explains how such flaws may occur, using a privacy preserving music matching problem as a template, and provides a solution, and analyzes the resulting tradeoff between privacy and computational complexity.
3
•Proceedings Article
Overview of computer-assisted language learning for european portuguese at l2f
Thomas Pellegrini,Wang Ling,A. Silva,Rui Correia,Isabel Trancoso,Jorge Baptista,Nuno J. Mamede +6 more
- 01 Jan 2012
TL;DR: An overview of the research in Computer-Assis ted Language Learning for European Portuguese is given, to show how the long-time experience in spoken language proc ssing allowed to propose multimedia documents as learning material.
3
Impact of vowel reduction in L2 Chinese learners of Portuguese within and across word boundaries.
Catarina Realinho,Rita Gonçalves,Helena Moniz,Isabel Trancoso +3 more
- 24 Mar 2021
TL;DR: The results reveal that word recognition is challenging for L2 learners due to the connected speech processes, and production analysis reveals that learners do not produce vowel reduction, nor any other phonetic-phonological phenomena across word boundaries.
3
Adaptation of SVM for MIL for inferring the polarity of movies and movie reviews
Joana Correia,Isabel Trancoso,Bhiksha Raj +2 more
- 01 Dec 2016
TL;DR: This work proposes two new adaptations of support vector machines (SVM) for MIL, θ-MIL, to suit this new scenario, and infer thePolarity of products and product reviews, and achieves a comparable performance to the SVM for MIL in accurately detecting the polarity of movies and movie reviews.
2