Number of documents
10
Meysam Shamsi is an Associate Professor in the Computer Science Department at Le Mans University. He joined the Language and Speech technology (LST) team in 2020 as a postdoctoral researcher to work on the autonomous system for speaker diarization by integrating lifelong learning. After 3 years of research in the University of Rennes 1, IRISA – Expression team, he received the Ph.D. degree in Computer Science in 2020.
Meysam has a background in Signal Processing (bachelor study in Electrical Engineering) and a Master of Artificial Intelligence. His primary research interests are Speech Processing, Human-Machine Interaction, Analysis of speech characteristic.
Journal articles1 document
-
yevhenii Prokopalo, Meysam Shamsi, Loïc Barrault, Sylvain Meignier, Anthony Larcher. Active Correction for Incremental Speaker Diarization of a Collection with Human in the Loop. Applied Sciences, MDPI, 2022, ⟨10.3390/app1010000⟩. ⟨hal-03563148⟩
Conference papers7 documents
-
yevhenii Prokopalo, Meysam Shamsi, Loïc Barrault, Sylvain Meignier, Anthony Larcher. Active correction for speaker diarization with human in the loop. Iberspeech, Mar 2021, Valladolid, Spain. ⟨hal-03262923⟩
-
Alexandre Flucha, Anthony Larcher, Ambuj Mehrish, Sylvain Meignier, Florian Plaut, et al.. The LIUM Human Active Correction Platform for Speaker Diarization. interspeech, Aug 2021, Brno, Czech Republic. ⟨hal-03262976⟩
-
Meysam Shamsi, Jonathan Chevelu, Nelly Barbot, Damien Lolive. Corpus design for expressive speech: impact of the utterance length. 10th International Conference on Speech Prosody 2020, May 2020, Tokyo, Japan. pp.955-959, ⟨10.21437/SpeechProsody.2020-195⟩. ⟨hal-02874005⟩
-
Meysam Shamsi. TTS voice corpus reduction for audio-book generation. 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 3 : Rencontre des Étudiants Chercheurs en Informatique pour le TAL, 2020, Nancy, France. pp.193-204. ⟨hal-02786200v3⟩
-
Meysam Shamsi, Damien Lolive, Nelly Barbot, Jonathan Chevelu. Investigating the relation between voice corpus design and hybrid synthesis under reduction constraint. 7th International Conference on Statistical Language and Speech Processing (SLSP), Oct 2019, Ljubljana, Slovenia. ⟨hal-02178406⟩
-
Meysam Shamsi, Damien Lolive, Nelly Barbot, Jonathan Chevelu. Corpus Design using Convolutional Auto-Encoder Embeddings for Audio-Book Synthesis. Interspeech, Sep 2019, Graz, Austria. ⟨hal-02159568⟩
-
Meysam Shamsi, Damien Lolive, Nelly Barbot, Jonathan Chevelu. Script Selection using Convolutional Auto-encoder for TTS Speech Corpus. International Conference on Speech and Computer (SPECOM), Aug 2019, Istanbul, Turkey. ⟨hal-02169465⟩
Book sections1 document
-
Meysam Shamsi, Nelly Barbot, Damien Lolive, Jonathan Chevelu. Mixing Synthetic and Recorded Signals for Audio-Book Generation. Speech and Computer (SPECOM) 2020, pp.479-489, 2020, ⟨10.1007/978-3-030-60276-5_46⟩. ⟨hal-02974346⟩
Theses1 document
-
Meysam Shamsi. Script optimization for TTS voice corpus design in audio-book generation. Computation and Language [cs.CL]. Université Rennes 1, 2020. English. ⟨NNT : 2020REN1S107⟩. ⟨tel-03270968⟩