Detection and classification of acoustic scenes and events: An IEEE AASP challenge
- D. Giannoulis, Emmanouil Benetos, D. Stowell, M. Rossignol, M. Lagrange, Mark D. Plumbley
- Computer ScienceIEEE Workshop on Applications of Signal…
- 2013
An overview of systems submitted to the public evaluation challenge on acoustic scene classification and detection of sound events within a scene as well as a detailed evaluation of the results achieved by those systems are provided.
A database and challenge for acoustic scene classification and event detection
- D. Giannoulis, D. Stowell, Emmanouil Benetos, M. Rossignol, M. Lagrange, Mark D. Plumbley
- Computer ScienceEuropean Signal Processing Conference
- 2013
This paper introduces a newly-launched public evaluation challenge dealing with two closely related tasks of the field: acoustic scene classification and event detection.
An empirical study of maximum entropy approach for part-of-speech tagging of Vietnamese texts
- Phuong Le-Hong, A. Roussanaly, Huyen Thi Minh Nguyen, M. Rossignol
- Computer ScienceJEPTALNRECITAL
- 19 July 2010
This paper presents an empirical study on the application of the maximum entropy approach for part-of-speech tagging of Vietnamese text, a language with special characteristics which largely…
Alternate level clustering for drum transcription
- M. Rossignol, M. Lagrange, G. Lafay, Emmanouil Benetos
- Computer ScienceEuropean Signal Processing Conference
- 1 September 2015
Comparison with state-of-the-art approaches demonstrate the potential of the proposed approach, both in terms of efficiency and of ability to generalize, to the problem of drum transcription.
Word Segmentation of Vietnamese Texts: a Comparison of Approaches
- Quang-Thang Dinh, Hong Phuong Le, Thi Minh Huyen Nguyen, Cam-Tu Nguyen, M. Rossignol, X. Vu
- LinguisticsInternational Conference on Language Resources…
- 28 May 2008
A comparison between three segmentation systems for the Vietnamese language confirms that it can be relatively well treated by automatic means, although a solution needs to be found to take into account out-of-vocabulary words.
A lexicon for Vietnamese language processing
- Huyen Thi Minh Nguyen, Laurent Romary, M. Rossignol, X. Vu
- Computer Science, LinguisticsLanguage Resources and Evaluation
- 26 July 2007
This paper presents the work on creating a Vietnamese lexicon for NLP applications and proposes an extensible set of Vietnamese syntactic descriptions that can be used for tagset definition and morphosyntactic analysis.
Automatic acquisition of lexical semantic information using medium to small corpora
- M. Rossignol, P. Sébillot
- Computer Science, LinguisticsWorkshop on Spoken Language Technologies for…
- 2008
This paper presents a system to assist the creation of semantic lexicons using small to medium-sized corpora, thanks to the combination of semantic class constitution and topic detection, and the development of specific statistical data analysis techniques for relatively small datasets.
A Morphological Model for Simulating Acoustic Scenes and Its Application to Sound Event Detection
- G. Lafay, M. Lagrange, M. Rossignol, Emmanouil Benetos, A. Röbel
- Computer ScienceIEEE/ACM Transactions on Audio Speech and…
- 1 October 2016
This paper introduces a model for simulating environmental acoustic scenes that abstracts temporal structures from audio recordings. This model allows us to explicitly control key morphological…
SimScene : a web-based acoustic scenes simulator
- M. Rossignol, G. Lafay, M. Lagrange, N. Misdariis
- Computer Science
- 26 January 2015
This paper introduces a soundscape simulator called SimScene, designed to be used as an experimental tool to characterize the mental representation of sound environments, developed in Javascript using the standard Web Audio technology, and thus fully supported by most modern web browsers.
Efficient similarity-based data clustering by optimal object to cluster reallocation
- M. Rossignol, M. Lagrange, Arshia Cont
- Computer SciencePLoS ONE
- 1 June 2018
This work presents an iterative flat hard clustering algorithm designed to operate on arbitrary similarity matrices, with the only constraint that these matrices be symmetrical, and shows that it significantly reduces memory access, which makes it a good choice for large data collections.
...
...