.

Bogdan Ludusan

Laboratoire de Sciences Cognitives et Psycholinguistique

EHESS/ENS/CNRS

email

Interests: prosody modelling, speech processing,
low/zero-resource approaches.



Bogdan




Short bio

Bogdan Ludusan is a postdoctoral researcher at the Laboratoire de Sciences Cognitives et Psycholinguistique, École Normale Supérieure, Paris. He is working with Emmanuel Dupoux on the Bootphon project, project that aims to model the process of language acquisition in infants.

Before this, he worked on automatic speech recognition, as a postdoctoral researcher at IRISA Rennes. Bogdan Ludusan graduated with an Engineering Diploma in Telecommunication from the Technical University of Cluj-Napoca and a PhD in Computer Science from the University of Naples “Federico II”.

His main research interests include various aspects of speech prosody (prominence, prosodic boundaries) from both a modelling perspective and a speech technology viewpoint.

Back To Top

Publications

Ludusan, B., Mazuka, R., Bernard, M., Cristia, A. and Dupoux, E., (accepted). The role of prosody and speech register in word segmentation: A computational modelling perspective, in Proceedings of ACL. (pdf)

Ludusan, B., Cristia, A., Martin, A., Mazuka, R. and Dupoux, E., (2016). Learnability of prosodic boundaries: Is infant-directed speech easier?, The Journal of the Acoustical Society of America, 140(2), 1239-1250. (pdf) Copyright (2016) Acoustical Society of America. This article may be downloaded for personal use only. Any other use requires prior permission of the author and the Acoustical Society of America. The following article appeared in JASA and may be found here

Ludusan, B. and Dupoux, E., (2016). The role of prosodic boundaries in word discovery: Evidence from a computational model, The Journal of the Acoustical Society of America, 140(1), EL1. (pdf)

Ludusan, B. and Dupoux, E., (2016). Automatic syllable segmentation using broad phonetic class information, in Proceedings of SLTU2016, pp. 101-106. (pdf)

Ludusan, B., Origlia, A. and Dupoux, E., (2015). Rhythm-based syllabic stress learning without labelled data, in Proceedings of SLSP2015, pp. 185-196. (pdf)

Ludusan, B., Caranica, A., Cucu, H., Buzo, A., Burileanu, C. and Dupoux, E. (2015). Exploring multi-language resources for unsupervised spoken term discovery, in Proceedings of SpeD2015, pp. 1-6. (pdf)

Ludusan, B., Seidl, A., Dupoux, E. and Cristia, A. (2015). Motif discovery in infant- and adult-directed speech, in Proceedings of CogACLL2015, pp. 93-102. (pdf)

Ludusan, B. and Dupoux, E., (2015). A multilingual study on intensity as a cue for marking prosodic boundaries, in Proceedings of ICPhS, paper 982. (pdf)

Wagner, P., Origlia, A., Avesani, C., Christodoulides, G., Cutugno, F., D’Imperio, M., Escudero Mancebo, D., Gili Fivela, B., Lacheret, A., Ludusan, B., Moniz, H., Ní Chasaide, A., Niebuhr, O., Rousier-Vercruyssen, L., Simon, A-C., Šimko, J., Tesser, F. and Vainio, M. (2015). Different parts of the same elephant: A roadmap to disentangle and connect different perspectives on prosodic prominence, in Proceedings of ICPhS, paper 202. (pdf)

Ludusan, B., Synnaeve, G. and Dupoux, E., (2015). Prosodic boundary information helps unsupervised word segmentation, in Proceedings of NAACL-HLT, pp. 953-963. (pdf)

Ludusan, B., Versteegh, M., Jansen, A., Gravier, G., Cao, X-N., Johnson, M. and Dupoux, E., (2014). Bridging the gap between speech technology and natural language processing: an evaluation toolbox for term discovery systems, in Proceedings of LREC'14, pp. 560-567. (pdf)

Ludusan, B., Gravier, G. and Dupoux, E., (2014). Incorporating prosodic boundaries in unsupervised term discovery, in Proceedings of Speech Prosody 7, pp. 939-943. (pdf)

Ludusan, B., Ziegler, S. and Gravier, G., (2014). Is syllable stress information robust for ASR in adverse conditions?, in Proceedings of Speech Prosody 7, pp. 207-211. (pdf)

Ludusan, B., and Dupoux, E., (2014). Towards low-resource prosodic boundary detection, in Proceedings of SLTU-2014, pp. 231-237. (pdf)

Ziegler, S., Ludusan, B. and Gravier, G., (2012). Towards a new speech event detection approach for landmark-driven speech recognition, In Proceedings of IEEE SLT 2012, pp. 342-347. (pdf)

Ludusan, B., Ziegler, S. and Gravier, G., (2012). Integrating stress information in large vocabulary continuous speech recognition, in Proceedings of INTERSPEECH-2012, pp. 2642-2645. (pdf)

Ziegler, S., Ludusan, B. and Gravier, G., (2012). Using broad phonetic classes to guide search in automatic speech recognition, in Proceedings of INTERSPEECH-2012, pp. 1023-1026. (pdf)

Cutugno, F., Leone, E., Ludusan, B. and Origlia, A., (2012). Investigating syllabic prominence with Conditional Random Fields and Latent-Dynamic Conditional Random Fields, in Proceedings of INTERSPEECH-2012, pp. 2402-2405. (pdf)

Leone, E., Origlia, A. and Ludusan, B., (2012). Conditional random fields come strumento di indagine per la rilevazione automatica di prominenze sillabiche, in Proceedings of the 8th National AISV Conference (in Italian). (pdf)

Ludusan, B., (2011). UNINA system for the EVALITA 2011 forced alignment task, In Evaluation of Natural Language and Speech Tools for Italian, Lecture Notes in Computer Science, vol. 7689, pp. 330-337, Springer Berlin Heidelberg. (pdf)

Ludusan, B., Origlia, A. and Cutugno, F., (2011). On the use of the rhythmogram for automatic syllabic prominence detection., in Proceedings of INTERSPEECH-2011, pp. 2413-2416. (pdf)

Origlia, A., Abete, G., Cutugno, F., Alfano, I., Savy, R., Ludusan, B., (2011). A divide et impera algorithm for optimal pitch stylization., in Proceedings of INTERSPEECH 2011, pp. 1993-1996. (pdf)

Cangemi, F., Cutugno, F., Ludusan, B., Seppi, D. and van Compernolle, D., (2011). Automatic speech segmentation for Italian: tools, models, evaluation, and applications., in Proceedings of the 7th National AISV Conference. (pdf)

Ludusan, B., Origlia, A. and Cutugno, F., (2010). Syllable classification using static matrices and prosodic features, in Proceedings of Speech Prosody. (pdf)

Origlia, A., Galatà, V. and Ludusan, B., (2010). Automatic classification of emotions via global and local prosodic features on a multilingual emotional database, in Proceedings of Speech Prosody. (pdf)

Abete, G., Cutugno, F., Ludusan, B. and Origlia, A., (2010). Pitch behavior detection for automatic prominence recognition, in Satellite Workshop of Speech Prosody. (pdf)

Piccolino-Boniforti, M.A., Ludusan, B., Hawkins, S. and Norris, D., (2010). Same phonemic sequence, different acoustic pattern and grammatical status. A model, in Proceedings of the 6th National AISV Conference. (pdf)

Cutugno, F., Ludusan, B., Origlia, A. and Soldo, S., (2009). Connected digits recognition using a syllable-based ASR system, in Poster and Workshop Proceedings of the 11th Conference of the Italian Association for Artificial Intelligence, ISBN 978-88-903581-1-1. (pdf)

Ludusan, B. and Soldo, S., (2009). Sonority-based syllable segmentation, in Proceedings of the 5th National AISV Conference. (pdf)

Soldo, S. and Ludusan, B., (2009). Statico vs dinamico, un possibile ruolo della sillaba nel riconoscimento automatico del parlato, in Proceedings of the 5th National AISV Conference (in Italian). (pdf)

Back To Top

Contact details

Laboratoire de Sciences Cognitives et Psycholinguistique
École Normale Supérieure
29 rue d'Ulm, Pavillon Jardin, office PJ16
75005, Paris
France
Phone no: +33(0)144322607

Back To Top

Links

Back To Top