-
Tanev, Hristo; Kouylekov, Milen Ognianov; Negri, Matteo; Coppola, Bonaventura; Magnini, Bernardo,Multilingual Pattern Libraries for Question Answering: a Case Study for Definition Questions,4th International Conference on Language Resources and Evaluation (LREC 2004),2004, pp. 1935-1938
-
Negri, Matteo,Sense-based Blind Relevance Feedback for Question Answering,SIGIR-2004 Workshop on Information Retrieval For Question Answering (IR4QA),2004
-
Negri, Matteo; Magnini, Bernardo,Using WordNet Predicates for Multilingual Named Entity Recognition,Second International WordNet Conference (GWC 2004),2004
-
Negri, Matteo; L., Marseglia,Recognition and Normalization of Time Expressions,2004
-
Pianta, Emanuele; Bentivogli, Luisa,Annotating Discontinuous Structures in XML: the Multiword Case,2003
-
Pianta, Emanuele; Bentivogli, Luisa,Translation as Annotation,AI*IA 2003 Workshop `Topics and Perspectives of Natural Language Processing in Italy`,2003, pp. 40-48
-
Bentivogli, Luisa; Girardi, Christian; Pianta, Emanuele,The MEANING Italian Corpus,Corpus Linguistics 2003 Conference,2003, pp. 103-112
-
Bentivogli, Luisa; Pianta, Emanuele,Beyond Lexical Units: Enriching WordNets with Phrasets,10th Conference of the European Chapter of the Association for Computational Linguistics (EACL`03),ACL,2003, pp. 67-70
-
Mana, Nadia; S., Burger; Cattoni, Roldano; L., Besacier; V., Maclaren; J., Mcdonough; F., Metze,The NESPOLE! VoIP Multilingual Corpora in Tourism and Medical Domains,Proceedings of Eurospeech 2003,2003, pp. 1589-1592
-
Mana, Nadia; S., Burger; Cattoni, Roldano; L., Besacier; Victoria, Maclaren; J., Mcdonough; F., Metze,The NESPOLE! VoIP Multilingual Corpora in Tourism and Medical Domains,2003
-
Mana, Nadia; Fauri, Elisabetta; Rossi, Franca; Cattoni, Roldano; Pianta, Emanuele; Pianesi, Fabio,The Italian NESPOLE! Corpus: a Multilingual Database with Interlingua Annotation in Tourism and Medical Domains,2003
-
Negri, Matteo; Magnini, Bernardo; Tanev, Hristo,Answer-Driven Reasoning as a Framework for Intelligent Information Access,AI*IA 2003,2003, pp. 76-83
-
Kouylekov, Milen Ognianov; Magnini, Bernardo; Negri, Matteo; Tanev, Hristo,ITC-irst at TREC 2003: the DIOGENE QA System,2003
-
Erwin, Leeuwis; Federico, Marcello; Cettolo, Mauro,Language Modeling and Transcription of the TED Corpus Lectures,ICASSP 2003,2003, pp. 232-235
-
Bertoldi, Nicola; Brugnara, Fabio; Cettolo, Mauro; Federico, Marcello; Giuliani, Diego; Erwin, Leeuwis; Sandrini, Vanessa,The ITC-irst News on Demand Platform,ECIR 2003,2003, pp. 520-527
-
Cettolo, Mauro; Michele, Vescovi,Efficient Audio Segmentation Algorithms based on the BIC,ICASSP 2003,2003, pp. 537-540
-
Michele, Vescovi; Cettolo, Mauro; Romeo, Rizzi,A DP Algorithm for Speaker Change Detection,Eurospeech 2003,2003, pp. 2997-3000
-
Cettolo, Mauro,Porting an Audio Partitioner Across Domains,ICASSP 2002,2002, pp. 301-304
-
Bertoldi, Nicola; Brugnara, Fabio; Cettolo, Mauro; Federico, Marcello; Giuliani, Diego,Cross-Task Portability of a Broadcast News Speech Recognition System,in «SPEECH COMMUNICATION»,vol. 38,n. 3-4,2002, pp. 335-347
-
Brugnara, Fabio; Cettolo, Mauro; Federico, Marcello; Giuliani, Diego,Issues in Automatic Transcription of Historical Audio Data,ICSLP 2002,2002, pp. 1441-1444
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