Section: Contracts and Grants with Industry
ARC INRIA RAPSODIS: Syntactic and Semantic Information-Based Automated Speech Recognition
Participant : Guillaume Gravier.
Duration: 2 years, starting in February 2008. Partners: Metiss , Parole , Talaris project-teams, CEA-LIST/LIC2M.
This project aims at improving automatic speech recognition (ASR) by integrating linguistic information. Based on former work by S. Huet concerning the incorporation of morpho-syntactic knowledge in a post-processing stage of the transcription, we experiment, together with our partners, the deep insertion of automatically obtained semantic relations (especially paradigmatic ones) and syntactic knowledge within an ASR system.
In 2009, the objectives of the project were extended to include semantic knowledge acquisition and the use of such knowledge for spoken document processing in addition to speech transcription. In this extended framework, we have worked on corpus-based acquisition of semantic relations for topic segmentation of spoken documents. We compared various classical methods for relation acquisition and measured their impact on out topic segmentation system.
QUAERO CTC and Corpus Projects (OSEO)
Main academic partners : IRCAM, IRIT, LIMSI, Telecom ParisTech
Quaero is a European research and development program with the goal of developing multimedia and multilingual indexing and management tools for professional and general public applications (such as search engines). The project was approved by The European Commission on 11 March 2008.
This program is supported by OSEO. The consortium is led by Thomson. Other companies involved in the consortium are: France Télécom, Exalead, Bertin Technologies, Jouve, Grass Valley GmbH, Vecsys, LTU Technologies, Siemens A.G. and Synapse Développement. Many public research institutes are also involved, including LIMSI-CNRS, INRIA, IRCAM, RWTH Aachen, University of Karlsruhe, IRIT, Clips/Imag, Telecom ParisTech, INRA, as well as other public organisations such as INA, BNF, LIPN and DGA.
METISS is involved in two technological domains : audio processing and music information retrieval (WP6). The research activities (CTC project) are focused on improving audio and music analysis, segmentation and description algorithms in terms of efficiency, robustness and scalability. Some effort is also dedicated on corpus design, collection and annotation (Corpus Project).
METISS also takes part to research and corpus activities in multimodal processing (WP10), in close collaboration with the Texmex project-team.
ANR Attelage de Systèmes Hétérogènes
Participant : Guillaume Gravier.
Duration: 3 years, starting in November 2009. Partners: IRISA/Metiss , LIA, LIUM
The project ASH (Automatic System Harnessing) aims at developing new collaborative paradigms for speech recognition. Many current ASR systems rely on an a posteriori combination of the output of several systems (e.g., confusion network combination). In the ASH project, we will investigate new approaches in which three ASR systems work in parallel, exchanging information at every step of the recognition process rather than limiting ourselves to an a posteriori combination. What information is to be shared and how to share such information and make use of it are the key questions that the project will address. The collaborative paradigm will be extended to landmark-based speech recognition where detection of landmarks and speech transcription will be considered as two (or more) collaborative processes.
Duration: 3 years (starting January 2009). Partners: A. Cohen, Laboratoire J. Louis Lions (Paris 6); F. Ollivier et J. Marchal, Laboratoire MPIA / Institut Jean Le Rond d'Alembert (Paris 6); L. Daudet, Laboratoire Ondes et Acoustique (Paris 6/7).
The objective of the ECHANGE project (ECHantillonage Acoustique Nouvelle GEnération) is to setup a theoretical and computational framework, based on the principles of compressed sensing, for the measurement and processing of complex acoustic fields through a limited number of acoustic sensors.