-
B., Chen; Cattoni, Roldano; Bertoldi, Nicola; Cettolo, Mauro; Federico, Marcello,The ITC-irst SMT System for IWSLT-2005,IWSLT 2005,2005
-
Cettolo, Mauro; Federico, Marcello; Bertoldi, Nicola; Cattoni, Roldano; B., Chen,A Look inside the ITC-irst SMT System,MT-Summit 2005,2005, pp. 451-457
-
Tanev, Hristo; Negri, Matteo; Magnini, Bernardo; Kouylekov, Milen Ognianov,The DIOGENE Question Answering System ad CLEF-2004,CLEF 2004,vol. 3491/2005,2005, pp. 325-333
-
Lavelli, Alberto; Magnini, Bernardo; Negri, Matteo; Pianta, Emanuele; Speranza, Manuela; Sprugnoli, Rachele,Italian Content Annotation Bank (I-CAB): Temporal Expressions (v. 1.0),2005
-
Magnini, Bernardo; Negri, Matteo; Tanev, Hristo; Kouylekov, Milen Ognianov,Bridging Languages for Question Answering,in «KI. KUNSTLICHE INTELLIGENZ»,n. 3/05,2005, pp. 11-17
-
Magnini, Bernardo; Negri, Matteo; Pianta, Emanuele; Romano, Lorenza; Speranza, Manuela; Serafini, Luciano; Girardi, Christian; V., Bartalesi; Sprugnoli, Rachele,Semantic Web Applications and Perspectives (SWAP 2005)2nd Italian Semantic Web Workshop,2005
-
V. H., Quan; Federico, Marcello; Cettolo, Mauro,Integrated N-best Re-ranking for Spoken Language Translation,Interspeech 2005,2005, pp. 3181-3184
-
Cettolo, Mauro; M., Vescovi; R., Rizzi,Evaluation of BIC-based Algorithms for Audio Segmentation,in «COMPUTER SPEECH AND LANGUAGE»,Elsevier,vol. 19,n. 2,2005, pp. 147-170
-
Cettolo, Mauro; Brugnara, Fabio; Federico, Marcello,Advances in the Automatic Transcription of Lectures,ICASSP 2004,2004, pp. 769-772
-
Cettolo, Mauro; Federico, Marcello,Minimum Error Training of Log-Linear Translation Models,IWSLT 2004,2004, pp. 103-106
-
Bentivogli, Luisa; A., Bocco; Pianta, Emanuele,ArchiWordNet: Integrating WordNet with Domain-Specific Knowledge,Second International WordNet Conference [GWC 2004],Masaryk University,2004, pp. 39-46
-
Bentivogli, Luisa; Pianta, Emanuele,Extending WordNet with Syntagmatic Information,Second International WordNet Conference [GWC 2004],Masaryk University,2004, pp. 47-53
-
M., Ranieri; Pianta, Emanuele; Bentivogli, Luisa,Browsing Multilingual Information with the MultiSemCor Web Interface,LREC 2004 Workshop on `The Amazing Utility of Parallel and Comparable Corpora`,European Language Resources Association,2004, pp. 38-41
-
Pianta, Emanuele; Bentivogli, Luisa,Annotating Discontinuous Structures in XML: the Multiword Case,LREC 2004 Satellite Workshop on XML-based richly annotated corpora,2004, pp. 30-37
-
Pianta, Emanuele; Bentivogli, Luisa,Knowledge Intensive Word Alignment with KNOWA,20th International Conference on Computational Linguistics [COLING 2004],ACL,2004, pp. 1086-1092
-
Bentivogli, Luisa; P., Forner; Magnini, Bernardo; Pianta, Emanuele,Revising the WORDNET DOMAINS Hierarchy: semantics, coverage and balancing,MLR2004: PostCOLING Workshop on Multilingual Linguistic Resources,2004, pp. 101-108
-
Bentivogli, Luisa; P., Forner; Pianta, Emanuele,Evaluating Cross-Language Annotation Transfer in the MultiSemCor Corpus,20th International Conference on Computational Linguistics [COLING 2004],ACL,2004, pp. 364-370
-
Mana, Nadia; Cattoni, Roldano; Pianta, Emanuele; F., Rossi; Pianesi, Fabio; S., Burger,The Italian NESPOLE! Corpus: A Multilingual Database with Interlingua Annotation in Tourism and Medical Domains,2004, pp. 1467-1470
-
Bertoldi, Nicola; Cattoni, Roldano; Cettolo, Mauro; Federico, Marcello,The ITC-irst Statistical Machine Translation System for IWSLT-2004,IWSLT 2004,2004, pp. 51-58
-
Negri, Matteo; Tanev, Hristo; Magnini, Bernardo,Bridging Languages for Question Answering DIOGENE at CLEF-2003,CLEF 2003,vol. 3237,2004, pp. 321-329
Our pick of the week by @mgaido91: "WhisperKit: On-device Real-time ASR with Billion-Scale Transformers" by Atila Orhon, Arda Okan, Berkin Durmus, @zachnagengast, and Eduardo Pacheco (ICML 2025)
#speech #speechtech #whisper #ASR #realtime
A couple of weeks before presenting our large-scale speech model compression task at IWSLT, here there is of the first attempts to bring large-scale models to the devices on the edge: https://arxiv.org/pdf/2507.10860... Hope to see more works along this direction!
Our pick of the week by @FBKZhihangXie: "Adversarial Speech-Text Pre-Training for Speech Translation" by Chenxuan Liu, Liping Chen, Weitai Zhang, Xiaoxi Li, Peiwang Tang, Mingjia Yu, Sreyan Ghosh, and Zhongyi Ye (ICASSP 2025)
#speech #speechprocessing #speechtech #translation
🚀 AdvST: Adversarial training aligns speech and text distributions without parallel data! Combines adversarial learning + hidden-state swapping to fix length mismatch & boost low-resource speech translation. https://ieeexplore.ieee.org/document/10888294
A special evening in Rome to talk about Physical AI and Europe’s role in shaping this new frontier.
Partners from across Europe came together to present the DVPS project, and connect with key people from public institutions, embassies, industries, national & international media.
Thrilled to be part of this amazing project and team!
🚀 DVPS has launched at Translated's HQ!
70 researchers from 20 institutions across 9 countries unite to build next-gen multimodal foundation models that learn from real-world interaction.
A new European AI journey begins.
#DVPS #PhysicalAI #HorizonEurope #MultimodalAI