-
G., Antoniol; Cettolo, Mauro; Federico, Marcello,Robust and Reliable Speech Understanding in Restricted Domains,IEEE Workshop on Automatic Speech Recognition,1993, pp. 103-104
-
G., Antoniol; Cettolo, Mauro; Federico, Marcello,Techniques for Robust Recognition in Restricted Domains,Eurospeech`93,1993, pp. 2219-2221
-
A., Antoniol; Brugnara, Fabio; Cettolo, Mauro; R., Fiutem; Flor, Roberto; Lazzari, Giannino,ASR System Comparison on New High Performance Workstation,Avios `93,1993, pp. 17-24
-
G., Antoniol; Brugnara, Fabio; Cettolo, Mauro; R., Fiutem; Flor, Roberto; Lazzari, Giannino,Comparison of Automatic Speech Recognition System based on New High Speed RISC Workstations,ICSPAT `93,1993, pp. 1473-1477
-
G., Antoniol; G., Carli; Cettolo, Mauro; R., Fiutem,Tools for Development, Test and Analysis of ASRs,ICSPAT `92,1992, pp. 1005-1010
-
G., Antoniol; G., Carli; Cettolo, Mauro; R., Fiutem; Flor, Roberto; Lazzari, Giannino,Finite State Network, Isolated Word, Real Time Automatic Speech Recognizer Based on DSP32C,ICSPAT `92,1992, pp. 1000-1004
-
Franco, Blanchini; Cettolo, Mauro; Patrizio, Righini,Disturbance Rejection Problem for Discrete-Time Linear Systems: a Comparison between Linear and Nonlinear Control,ISIRS `91,1991, pp. 28-32
-
Cattoni, Roldano; E., Franconi,Walking through the Semantics of Frame-Based Description Languages: A Case study,1990
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
Cosa chiedono davvero gli italiani all’intelligenza artificiale?
FBK in collaborazione con RiTA lancia un’indagine aperta a tutte/i per capire usi reali, abitudini e bisogni.
Bastano 10 minuti per partecipare, scopri di più: https://magazine.fbk.eu/it/news/italiani-e-ia-cosa-chiediamo-veramente-allintelligenza-artificiale/
🚀 Last call for the Model Compression for Machine Translation task at #WMT2025 (co-located with #EMNLP2025)!
Test data out on June 19 ➡️ 2 weeks for evaluation!
Can you shrink an LLM and keep translation quality high?
👉 https://www2.statmt.org/wmt25/model-compression.html #NLP #ML #LLM #ModelCompression
Our pick of the week by @beomseok_lee_: "ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs" by Pooneh Mousavi, @yingzhi_wang, @mirco_ravanelli, and @CemSubakan (2025)
#SLU #speech #multimodal #LLM
Speech-language models show promise in multimodal tasks—but how well are speech & text actually aligned? 🤔
This paper https://arxiv.org/abs/2505.19937 proposes a new metric to measure layer-wise correlation between the two, with a focus on SLU tasks. 🔍🗣️📄