-
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
Our pick of the week by @FBKZhihangXie: "PHRASED: Phrase Dictionary Biasing for Speech Translation" by Peidong Wang, Jian Xue, Rui Zhao, @ChenJunkun, Aswin Shanmugam Subramanian, and Jinyu Li (2025).
#Speech #SpeechAI #Translation #ST #SpeechTranslation
🚀 Boost rare-phrase translation in speech! Uses **bilingual dictionaries** to dynamically bias outputs.
✅ **+21%** recall in streaming ST
✅ **+85%** in multimodal LLMs
🔗: http://arxiv.org/abs/2506.09175
FAMA è il primo foundation model vocale open-science per ita e eng, sviluppato da FBK. Riconosce e traduce la voce usando solo dati e strumenti pubblici: oltre 150.000 ore di audio open, codice e processi completamente accessibili.
@fbk_stek @fbk_mt
https://magazine.fbk.eu/it/news/la-prima-famiglia-di-modelli-open-science-per-il-riconoscimento-vocale-e-la-traduzione-del-parlato/
Emanuele Pianta Award for the Best Master’s Thesis in Computational Linguistics submitted at an Italian university and defended between August 1st 2024 and July 31st 2025
- Deadline: August 1st, 2025 (11:59 pm CEST)
- All details online: https://clic2025.unica.it/emanuele-pianta-award-for-the-best-masters-thesis/
Our pick of the week by @DennisFucci: "Speech Representation Analysis Based on Inter- and Intra-Model Similarities" by Yassine El Kheir, Ahmed Ali, and Shammur Absar Chowdhury (ICASSP Workshops 2024)
#speech #speechtech
Findings from https://ieeexplore.ieee.org/document/10669908 show that speech SSL models converge on similar embedding spaces, but via different routes. While overall representations align, individual neurons learn distinct localized concepts.
Interesting read! @fbk_mt