Archivio Istituzionale della RicercaKOUDOUNAS, ALKIS
KOUDOUNAS, ALKIS
Dipartimento di Automatica e Informatica
070128
A Concept-based approach to Voice Disorder Detection
In corso di stampa Ghia, Davide; Ciravegna, Gabriele; Koudounas, Alkis; Fantini, Marco; Crosetti, Erika; Succo, Giovanni; Cerquitelli, Tania
Toward Robust, Responsible and Trustworthy Speech Foundation Models
2026 Koudounas, Alkis
"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
2025 Koudounas, Alkis; Savelli, Claudio; Giobergia, Flavio; Baralis, Elena
"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding
2025 Koudounas, Alkis; La Quatra, Moreno; Pastor, Eliana; Marco Siniscalchi, Sabato; Baralis, Elena
Boosting court judgment prediction and explanation using legal entities
2025 Benedetto, Irene; Koudounas, Alkis; Vaiani, Lorenzo; Pastor, Eliana; Cagliero, Luca; Tarasconi, Francesco; Baralis, Elena
Detecting and Mitigating Challenges in Zero-Shot Video Summarization with Video LLMs
2025 Cagliero, Luca; Vaiani, Lorenzo; Pastor, Eliana; Koudounas, Alkis; Baralis, Elena; Mazzia, Vittorio; Pollastrini, Sandro; Gueudre, Thomas; Giollo, Manuel; Amberti, Daniele; Wu, Yue
Exploring Generative Error Correction for Dysarthric Speech Recognition
2025 La Quatra, Moreno; Koudounas, Alkis; Mario Salerno, Valerio; Marco Siniscalchi, Sabato
MALTO at SemEval-2025 task 3: Detecting hallucinations in LLMs via uncertainty quantification and larger model validation
2025 Savelli, Claudio; Koudounas, Alkis; Giobergia, Flavio
Mitigating Subgroup Disparities in Speech Models: A Divergence-Aware Dual Strategy
2025 Koudounas, Alkis; Pastor, Eliana; Alfaro, Luca de; Baralis, Elena
Multimodal Fusion Techniques to Enhance Voice Disorder Diagnoses
2025 Liu, Qingqing; Ciravegna, Gabriele; Koudounas, Alkis; Cerquitelli, Tania; Baralis, Elena
MVP: Multi-source Voice Pathology detection
2025 Koudounas, Alkis; La Quatra, Moreno; Ciravegna, Gabriele; Fantini, Marco; Crosetti, Erika; Succo, Giovanni; Cerquitelli, Tania; Marco Siniscalchi, Sabato; Baralis, Elena
Privacy Preserving Data Selection for Bias Mitigation in Speech Models
2025 Koudounas, Alkis; Pastor, Eliana; Mazzia, Vittorio; Giollo, Manuel; Gueudre, Thomas; Reale, Elisa; Cagliero, Luca; Cumani, Sandro; De Alfaro, Luca; Baralis, Elena; Amberti, Daniele
Quantum feature selection from interpretable models using qubo formulation
2025 Giobergia, Flavio; Savelli, Claudio; Koudounas, Alkis; Baralis, Elena Maria
voc2vec: A Foundation Model for Non-Verbal Vocalization
2025 Koudounas, Alkis; La Quatra, Moreno; Siniscalchi, Sabato Marco; Baralis, Elena
A Contrastive Learning Approach to Mitigate Bias in Speech Models
2024 Koudounas, Alkis; Giobergia, Flavio; Pastor, Eliana; Baralis, Elena
Ainur: Harmonizing Speed and Quality in Deep Music Generation Through Lyrics-Audio Embeddings
2024 Concialdi, Giuseppe; Koudounas, Alkis; Pastor, Eliana; Di Eugenio, Barbara; Baralis, Elena
Assessing Speech Model Performance: A Subgroup Perspective
2024 Koudounas, Alkis; Pastor, Eliana; Baralis, Elena
Benchmarking Representations for Speech, Music, and Acoustic Events
2024 LA QUATRA, Moreno; Koudounas, Alkis; Vaiani, Lorenzo; Baralis, Elena; Cagliero, Luca; Garza, Paolo; Marco Siniscalchi, Sabato
Ex(o)plain: Subgroup-level analysis of exoplanet atmospheric parameters
2024 Koudounas, Alkis; Giobergia, Flavio; Baralis, Elena
Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features
2024 Pastor, Eliana; Koudounas, Alkis; Attanasio, Giuseppe; Hovy, Dirk; Baralis, Elena
| Citazione | Data di pubblicazione | Autori | File |
|---|---|---|---|
| A Concept-based approach to Voice Disorder Detection / Ghia, D., Ciravegna, G., Koudounas, A., Fantini, M., Crosetti, E., Succo, G., Cerquitelli, T.. - (In corso di stampa). (European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2025 - Workshop & Tutorial Track Porto (PRT) September 15-19, 2025). | In corso di stampa | Davide GhiaGabriele CiravegnaAlkis KoudounasTania Cerquitelli + | - |
| Toward Robust, Responsible and Trustworthy Speech Foundation Models / Koudounas, Alkis. - (2026 Jan 19), pp. 1-311. [10.13121/polito/porto/3006974] | 19-gen-2026 | KOUDOUNAS, ALKIS | Koudounas_PhD_Thesis.pdf; Koudounas_Thesis_Abstract.pdf |
| "Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding / Koudounas, A., Savelli, C., Giobergia, F., Baralis, E.. - (2025), pp. 1768-1772. (Interspeech 2025 Rotterdam (NL) 17-21 August, 2025) [10.21437/Interspeech.2025-2607]. | 1-gen-2025 | Alkis KoudounasClaudio SavelliFlavio GiobergiaElena Baralis | koudounas25c_interspeech.pdf |
| "KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding / Koudounas, A., La Quatra, M., Pastor, E., Marco Siniscalchi, S., Baralis, E.. - (2025), pp. 4123-4127. (Interspeech 2025 Rotterdam (NL) 17-21 August, 2025) [10.21437/Interspeech.2025-1612]. | 1-gen-2025 | Alkis KoudounasEliana PastorElena Baralis + | koudounas25_interspeech.pdf |
| Boosting court judgment prediction and explanation using legal entities / Benedetto, I., Koudounas, A., Vaiani, L., Pastor, E., Cagliero, L., Tarasconi, F., Baralis, E.. - In: ARTIFICIAL INTELLIGENCE AND LAW. - ISSN 0924-8463. - ELETTRONICO. - 33:3(2025), pp. 605-640. [10.1007/s10506-024-09397-8] | 1-gen-2025 | Benedetto, IreneKoudounas, AlkisVaiani, LorenzoPastor, ElianaCagliero, LucaBaralis, Elena + | s10506-024-09397-8.pdf |
| Detecting and Mitigating Challenges in Zero-Shot Video Summarization with Video LLMs / Cagliero, L., Vaiani, L., Pastor, E., Koudounas, A., Baralis, E., Mazzia, V., Pollastrini, S., Gueudre, T., Giollo, M., Amberti, D., Wu, Y.. - (2025), pp. 286-301. (63rd Annual Meeting of the Association for Computational Linguistics: ACL 2025 Vienna (AT) 27Jul - 1 Aug 2025). | 1-gen-2025 | Cagliero, LucaVaiani, LorenzoPastor, ElianaKoudounas, AlkisBaralis, Elena + | 2025.findings-acl.16.pdf |
| Exploring Generative Error Correction for Dysarthric Speech Recognition / La Quatra, M., Koudounas, A., Mario Salerno, V., Marco Siniscalchi, S.. - (2025), pp. 3284-3288. (Interspeech 2025 Rotterdam (NL) 17-21 August, 2025) [10.21437/Interspeech.2025-1553]. | 1-gen-2025 | Alkis Koudounas + | laquatra25_interspeech.pdf |
| MALTO at SemEval-2025 task 3: Detecting hallucinations in LLMs via uncertainty quantification and larger model validation / Savelli, C., Koudounas, A., Giobergia, F.. - (2025), pp. 1318-1324. (19th International Workshop on Semantic Evaluation (SemEval-2025) Vienna (AT) July 31 - August 1, 2025). | 1-gen-2025 | Savelli ClaudioKoudounas AlkisGiobergia Flavio | 2025.semeval-1.175.pdf |
| Mitigating Subgroup Disparities in Speech Models: A Divergence-Aware Dual Strategy / Koudounas, A., Pastor, E., Alfaro, L.d., Baralis, E.. - In: IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING. - ISSN 2329-9290. - 33:(2025), pp. 883-895. [10.1109/taslpro.2025.3539429] | 1-gen-2025 | Koudounas, AlkisPastor, ElianaBaralis, Elena + | Mitigating_Subgroup_Disparities_in_Speech_Models_A_Divergence-Aware_Dual_Strategy.pdf; Mitigating_Subgroup_Disparities_in_Speech_Models_ postprint.pdf |
| Multimodal Fusion Techniques to Enhance Voice Disorder Diagnoses / Liu, Q., Ciravegna, G., Koudounas, A., Cerquitelli, T., Baralis, E.. - 3946:(2025). (Workshops of the EDBT/ICDT 2025 Joint Conference, DARLI-AP Workshop Barcelona (ESP) 25-28 March, 2025). | 1-gen-2025 | Gabriele CiravegnaAlkis KoudounasTania CerquitelliElena Baralis + | DARLI-AP-10.pdf |
| MVP: Multi-source Voice Pathology detection / Koudounas, A., La Quatra, M., Ciravegna, G., Fantini, M., Crosetti, E., Succo, G., Cerquitelli, T., Marco Siniscalchi, S., Baralis, E.. - (2025), pp. 3548-3552. (Interspeech 2025 Rotterdam (NL) 17-21 August, 2025) [10.21437/Interspeech.2025-1868]. | 1-gen-2025 | Alkis KoudounasTania CerquitelliElena Baralis + | koudounas25b_interspeech.pdf |
| Privacy Preserving Data Selection for Bias Mitigation in Speech Models / Koudounas, A., Pastor, E., Mazzia, V., Giollo, M., Gueudre, T., Reale, E., Cagliero, L., Cumani, S., De Alfaro, L., Baralis, E., Amberti, D.. - 6: Industry track:(2025), pp. 738-748. (63rd Annual Meeting of the Association for Computational Linguistics: ACL 2025 Vienna (AT) 27Jul - 1 Aug 2025). | 1-gen-2025 | Koudounas, AlkisPastor, ElianaCagliero, LucaCumani, SandroBaralis, Elena + | 2025.acl-industry.52.pdf |
| Quantum feature selection from interpretable models using qubo formulation / Giobergia, F., Savelli, C., Koudounas, A., Baralis, E.M.. - (2025). (CLEF 2025 Madrid (ESP) 9 – 12 September 2025). | 1-gen-2025 | Giobergia FlavioSavelli ClaudioKoudounas AlkisBaralis Elena | paper_340.pdf |
| voc2vec: A Foundation Model for Non-Verbal Vocalization / Koudounas, A., La Quatra, M., Siniscalchi, S.M., Baralis, E.. - (2025), pp. 1-5. (2025 IEEE International Conference on Acoustics, Speech and Signal Processing Hyderabad (IND) 06-11 April 2025) [10.1109/icassp49660.2025.10890672]. | 1-gen-2025 | Koudounas, AlkisBaralis, Elena + | voc2vec_A_Foundation_Model_for_Non-Verbal_Vocalization.pdf |
| A Contrastive Learning Approach to Mitigate Bias in Speech Models / Koudounas, A., Giobergia, F., Pastor, E., Baralis, E.. - (2024), pp. 827-831. (Interspeech 2024 Kos (GRC) 1-5 September 2024) [10.21437/interspeech.2024-1219]. | 1-gen-2024 | Koudounas, AlkisGiobergia, FlavioPastor, ElianaBaralis, Elena | koudounas24b_interspeech.pdf |
| Ainur: Harmonizing Speed and Quality in Deep Music Generation Through Lyrics-Audio Embeddings / Concialdi, G., Koudounas, A., Pastor, E., Di Eugenio, B., Baralis, E.. - (2024), pp. 1146-1150. (2024 IEEE International Conference on Acoustics, Speech and Signal Processing Seoul (KOR) 14-19 April, 2024) [10.1109/icassp48485.2024.10448078]. | 1-gen-2024 | Koudounas, AlkisPastor, ElianaBaralis, Elena + | Ainur_Harmonizing_Speed_and_Quality_in_Deep_Music_Generation_Through_Lyrics-Audio_Embeddings.pdf |
| Assessing Speech Model Performance: A Subgroup Perspective / Koudounas, A., Pastor, E., Baralis, E.. - 3741:(2024), pp. 101-111. (SEBD 2024: 32nd Symposium on Advanced Database System Villasimius, Sardinia (IT) 23-26 June, 2024). | 1-gen-2024 | Koudounas, AlkisPastor, ElianaBaralis, Elena | paper64.pdf |
| Benchmarking Representations for Speech, Music, and Acoustic Events / LA QUATRA, M., Koudounas, A., Vaiani, L., Baralis, E., Cagliero, L., Garza, P., Marco Siniscalchi, S.. - (2024), pp. 505-509. (2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) Seoul (KOR) 14-19 April 2024) [10.1109/ICASSPW62465.2024.10625960]. | 1-gen-2024 | Moreno La QuatraAlkis KoudounasLorenzo VaianiElena BaralisLuca CaglieroPaolo Garza + | 2405.00934v1.pdf; Benchmarking_Representations_for_Speech_Music_and_Acoustic_Events.pdf |
| Ex(o)plain: Subgroup-level analysis of exoplanet atmospheric parameters / Koudounas, A., Giobergia, F., Baralis, E.. - In: IEEE ACCESS. - ISSN 2169-3536. - 12:(2024), pp. 139773-139788. [10.1109/access.2024.3466919] | 1-gen-2024 | Koudounas, AlkisGiobergia, FlavioBaralis, Elena | Exoplain_Subgroup-Level_Analysis_of_Exoplanet_Atmospheric_Parameters.pdf |
| Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features / Pastor, E., Koudounas, A., Attanasio, G., Hovy, D., Baralis, E.. - 1: Long Papers:(2024), pp. 2221-2238. (18th Conference of the European Chapter of the Association for Computational Linguistics Malta March 17-22, 2024). | 1-gen-2024 | Eliana PastorAlkis KoudounasElena Baralis + | 2024.eacl-long.136.pdf |