-
Cattoni, Roldano; M., Danieli; A., Panizza; Sandrini, Vanessa; C., Soria,Building a corpus of annotate dialogues: the ADAM experience,Proceedings of Corpus Linguistics 2001,2001
-
Cattoni, Roldano; Federico, Marcello; A., Lavie,Robust Analysis of Spoken Input combining Statistical and Knowledge-based Information Sources,Proceedings of the 2001 IEEE Workshop on Automatic Speech Recognition and Understanding,2001
-
Magnini, Bernardo; Negri, Matteo; Prevete, Roberto,Open Domain Question/Answering on the Web,Proceedings of AI*IA 2001: Advances in Artificial Intelligence, 7th Congress of the Italian Association for Artificial Intelligence,Springer,2001, pp. 273-284
-
Magnini, Bernardo; Negri, Matteo; Prevete, Roberto; Tanev, Hristo,Multilingual Question/Answering: the DIOGENE System,TREC 2001,2001, pp. 425-433
-
Bertoldi, Nicola; Brugnara, Fabio; Cettolo, Mauro; Federico, Marcello; Giuliani, Diego,From Broadcast News to Spontraneous Dialogue Transcription: Portability Issues,ICASSP 2001,2001, pp. 37-40
-
Cettolo, Mauro,Speaker Tracking in a Broadcast News Corpus,2001: A Speaker Odyssey - The Speaker Recognition Workshop,2001, pp. 163-167
-
Cettolo, Mauro,Segmentation, Classification and Clustering of an Italian Broadcast News Corpus,RIAO 2000,2000, pp. 372-381
-
Brugnara, Fabio; Cettolo, Mauro; Federico, Marcello; Giuliani, Diego,A System for the Segmentation and Transcription of Italian Radio News,RIAO 2000,2000, pp. 364-371
-
Cettolo, Mauro,You talk, I translate! Technical Aspects of the ITC-irst Speech Translation System,2000
-
Brugnara, Fabio; Cettolo, Mauro; Federico, Marcello; Giuliani, Diego,Advances in Automatic Transcription of Italian Broadcast News,ICSLP 2000,2000, pp. 660-663
-
Cettolo, Mauro; Federico, Marcello,Model Selection Criteria for Acoustic Segmentation,ISCA ITRW ASR2000,2000, pp. 221-227
-
Brugnara, Fabio; Cettolo, Mauro; Federico, Marcello; Giuliani, Diego,A Baseline for the Transcription of Italian Broadcast News,ICASSP 2000,2000, pp. 1667-1670
-
Bentivogli, Luisa; Pianesi, Fabio; Pianta, Emanuele,From Word-based to Concept-based Text Analysis: the PhiloNet Project,Workshop Informatica umanistica: filosofia e risorse digitali,2000
-
Bentivogli, Luisa; Pianta, Emanuele,Looking for Lexical Gaps,Ninth EURALEX International Congress [EURALEX 2000],2000, pp. 663-669
-
Bentivogli, Luisa; Pianta, Emanuele; Pianesi, Fabio,Coping with Lexical Gaps when Building Aligned Multilingual Wordnets,Second International Conference on Language Resources and Evaluation (LREC 2000),2000, pp. 993-997
-
C., Soria; Cattoni, Roldano; M., Danieli,ADAM: An Architecture for xml-based Dialogue Annotation on Multiple levels,Proceedings of the 1st SIGdial Workshop on Discourse and Dialogue, in conjuction with ACL-2000: The 38th Annual Meeting of the Association for Computational Linguistics,2000
-
P., Charlton; Cattoni, Roldano; Potrich, Alessandra; E., Mamdani,Evaluating the FIPA Standards and Its Role in Achieving Cooperation in Multi-agent Systems,Proceedings of Thirty-Third Annual Hawaii International Conference on System Sciences,2000
-
Negri, Matteo,La valutazione di moduli nell`elaborazione del linguaggio naturale: problemi e metodi,2000
-
Bentivogli, Luisa,Relazioni lessicali e semantiche nella costruzione di un lessico computazionale multilingue: Problematiche Tecniche e Filosofiche,1999
-
Trentin, Edmondo; Cattoni, Roldano,A Hybrid Framework for Indoor Robot Navigation,Marinaro M., Tagliaferri R. (eds.), Neural Nets WIRN-98, Section 6m Pattern Recognition and Signal Processing,1999, pp. 255-263
๐ New tech report out! Meet FAMA, our open-science speech foundation model family for both ASR and ST in ๐ฌ๐ง English and ๐ฎ๐น Italian.
The models are live and ready to try on @huggingface ๐
๐
#ASR #ST #OpenScience #MultilingualAI
Our pick of the week by @lina_conti: "Languages in Multilingual Speech Foundation Models Align Both Phonetically and Semantically" by @soheunshim, Domenico De Cristofaro, Chengzhi Martin Hu, Alessandro Vietti, and @barbara_plank (2025).
#speech #SFM #multilingual #speechtech
Pick of the week @fbk_mt: https://arxiv.org/abs/2505.19606 by @soheunshim @DomenicoDeCris1. XAI work on cross-lingual alignment in speech-to-text models that disentangles phonetics and semantics. Plus: their XAI insights yield actionable improvements for low-resource language performance.
๐ New shared task at #WMT2025 (co-located with @emnlpmeeting ): Model Compression for Machine Translation!
Can you shrink an LLM and keep translation quality high?๐ง
Submit by July 3 and push the limits of efficient NLP!
๐ https://www2.statmt.org/wmt25/model-compression.html #NLP #ML #LLM #ModelCompression
More great news! ๐
Our paper โEchoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attributionโ was accepted at #Interspeech2025!
Interested in interpretability for speech models? Preprint coming soon!
โ๐ผ @mgaido91, @negri_teo, M.Cettolo, @luisabentivogli