Mirco Ravanelli

Identifiers

• name variant Mirco Ravanelli 0.60 · backfill

Papers (78)

1. HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models cs.LG · 2026 · author #4
2. Adaptive Order Policies for Masked Diffusion cs.LG · 2026 · author #3
3. Exploring Token-Space Manipulation in Latent Audio Tokenizers cs.SD · 2026 · author #3
4. Investigating Faithfulness in Large Audio Language Models cs.LG · 2025 · author #3
5. Audio Prototypical Network For Controllable Music Recommendation cs.IR · 2025 · author #5
6. Autoregressive Speech Enhancement via Acoustic Tokens cs.SD · 2025 · author #3
7. From Black Box to Biomarker: Sparse Autoencoders for Interpreting Speech Models of Parkinson's Disease eess.AS · 2025 · author #4
8. Does Language Matter for Early Detection of Parkinson's Disease from Speech? eess.AS · 2025 · author #4
9. ALAS: An Automatic Latent Alignment Score for Audio Language Models cs.CL · 2025 · author #3
10. LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs cs.AI · 2025 · author #4
11. Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down cs.CL · 2025 · author #5
12. Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech cs.SD · 2024 · author #4
13. Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve? cs.CL · 2024 · author #4
14. Dynamic HumTrans: Humming Transcription Using CNNs and Dynamic Programming cs.LG · 2024 · author #4
15. What Are They Doing? Joint Audio-Speech Co-Reasoning cs.SD · 2024 · author #4
16. LMAC-TD: Producing Time Domain Explanations for Audio Classifiers cs.SD · 2024 · author #3
17. ProGRes: Prompted Generative Rescoring on ASR n-Best cs.CL · 2024 · author #3
18. Open-Source Conversational AI with SpeechBrain 1.0 cs.LG · 2024 · author #1
19. DASB - Discrete Audio and Speech Benchmark cs.SD · 2024 · author #8
20. How Should We Extract Discrete Audio Tokens from Self-Supervised Models? cs.SD · 2024 · author #7
21. Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice eess.AS · 2024 · author #2
22. Listenable Maps for Zero-Shot Audio Classifiers cs.SD · 2024 · author #3
23. Listenable Maps for Audio Classifiers cs.SD · 2024 · author #2
24. SKILL: Similarity-aware Knowledge distILLation for Speech Self-Supervised Learning eess.AS · 2024 · author #4
25. Focal Modulation Networks for Interpretable Sound Classification cs.SD · 2024 · author #3
26. Bayesian Deep Learning for Remaining Useful Life Estimation via Stein Variational Gradient Descent cs.LG · 2024 · author #4
27. Are LLMs Robust for Spoken Dialogues? cs.CL · 2024 · author #5
28. Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers eess.AS · 2023 · author #4
29. TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch eess.AS · 2023 · author #16
30. CL-MASR: A Continual Learning Benchmark for Multilingual ASR cs.CL · 2023 · author #5
31. Audio Editing with Non-Rigid Text Prompts cs.SD · 2023 · author #4
32. Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets cs.LG · 2023 · author #27
33. Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads eess.AS · 2023 · author #5
34. Generalization Limits of Graph Neural Networks in Identity Effects Learning cs.LG · 2023 · author #3
35. Speech Emotion Diarization: Which Emotion Appears When? cs.CL · 2023 · author #2
36. RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain eess.AS · 2023 · author #2
37. Speech Self-Supervised Representation Benchmarking: Are We Doing it Right? eess.AS · 2023 · author #5
38. Simulated Annealing in Early Layers Leads to Better Generalization cs.LG · 2023 · author #5
39. Posthoc Interpretation via Quantization cs.AI · 2023 · author #3
40. Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study eess.AS · 2023 · author #5
41. SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation cs.SD · 2022 · author #2
42. Resource-Efficient Separation Transformer eess.AS · 2022 · author #3
43. Learning Representations for New Sound Classes With Continual Self-Supervised Learning eess.AS · 2022 · author #6
44. Exploring Self-Attention Mechanisms for Speech Separation eess.AS · 2022 · author #2
45. OSSEM: one-shot speaker adaptive speech enhancement using meta learning eess.AS · 2021 · author #5
46. REAL-M: Towards Speech Separation on Real Mixtures eess.AS · 2021 · author #2
47. MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech cs.SD · 2021 · author #4
48. Interpretable SincNet-based Deep Learning for Emotion Recognition from EEG brain activity eess.SP · 2021 · author #2
49. SpeechBrain: A General-Purpose Speech Toolkit eess.AS · 2021 · author #1
50. MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement cs.SD · 2021 · author #5
51. Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers cs.CL · 2021 · author #3
52. ECAPA-TDNN Embeddings for Speaker Diarization eess.AS · 2021 · author #2
53. Transformers with Competitive Ensembles of Independent Mechanisms cs.LG · 2021 · author #6
54. Attention is All You Need in Speech Separation eess.AS · 2020 · author #2
55. BIRD: Big Impulse Response Dataset cs.SD · 2020 · author #4
56. Quaternion Neural Networks for Multi-channel Distant Speech Recognition eess.AS · 2020 · author #3
57. Multi-task self-supervised learning for Robust Speech Recognition eess.AS · 2020 · author #1
58. Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models eess.AS · 2019 · author #4
59. Speech Model Pre-training for End-to-End Spoken Language Understanding eess.AS · 2019 · author #2
60. Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks cs.LG · 2019 · author #2
61. Speech and Speaker Recognition from Raw Waveform with SincNet eess.AS · 2018 · author #1
62. Learning Speaker Representations with Mutual Information eess.AS · 2018 · author #1
63. Interpretable Convolutional Filters with SincNet eess.AS · 2018 · author #1
64. Speech recognition with quaternion neural networks eess.AS · 2018 · author #2
65. The PyTorch-Kaldi Speech Recognition Toolkit eess.AS · 2018 · author #1
66. Speaker Recognition from Raw Waveform with SincNet eess.AS · 2018 · author #1
67. Quaternion Recurrent Neural Networks stat.ML · 2018 · author #2
68. Automatic context window composition for distant speech recognition eess.AS · 2018 · author #1
69. Twin Regularization for online speech recognition eess.AS · 2018 · author #1
70. Light Gated Recurrent Units for Speech Recognition eess.AS · 2018 · author #1
71. Deep Learning for Distant Speech Recognition cs.CL · 2017 · author #1
72. Realistic multi-microphone data simulation for distant speech recognition eess.AS · 2017 · author #1
73. Audio Concept Classification with Hierarchical Deep Neural Networks eess.AS · 2017 · author #1
74. Contaminated speech training methods for robust DNN-HMM distant speech recognition eess.AS · 2017 · author #1
75. The DIRHA-English corpus and related tasks for distant-speech recognition in domestic environments eess.AS · 2017 · author #1
76. Improving speech recognition by revising gated recurrent units cs.CL · 2017 · author #1
77. Batch-normalized joint training for DNN-based distant speech recognition cs.CL · 2017 · author #1
78. A network of deep neural networks for distant speech recognition cs.CL · 2017 · author #1

Mentions

• 2508.00194 #5 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2507.16836 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2507.16832 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2507.12825 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2505.18517 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2505.12969 #5 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2405.17615 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2409.14526 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2411.08013 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2407.00463 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2410.05581 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2410.05455 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2406.10422 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2310.12858 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2409.08655 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2409.00217 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2312.03694 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2403.13086 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2406.10735 #7 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2402.16830 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2308.14456 #5 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2402.02754 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2402.01098 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2206.09507 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2401.02297 #5 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2307.00134 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2310.17864 #16 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2310.16931 #5 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2306.12991 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2310.04292 #27 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2306.04054 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2306.00452 #5 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2303.12659 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2202.02884 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2304.04858 #5 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2303.06740 #5 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2205.07390 #6 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2207.13703 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2111.05703 #5 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2110.10812 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2110.05866 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2104.01604 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2104.01466 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2107.10790 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2106.04624 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2104.03538 #5 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2010.13154 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2103.00336 #6 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2010.09930 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2005.08566 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2001.09239 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1910.09463 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1811.09725 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1808.00158 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1904.03670 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1904.03416 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1812.00271 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1812.05920 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1811.07453 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1806.04418 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1811.09678 #2 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1804.05374 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1805.10498 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1803.10225 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1712.06086 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1711.09470 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1710.04288 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1710.03538 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1710.02560 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1710.00641 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1703.08471 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 1703.08002 #1 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2606.27627 #4 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2509.22363 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2505.19937 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli
• 2606.00295 #3 · arxiv_oai · confidence 0.70 Mirco Ravanelli

Frequent Coauthors

• Cem Subakan 26 shared papers
• Yoshua Bengio 17 shared papers
• Luca Della Libera 11 shared papers
• Titouan Parcollet 10 shared papers
• Francesco Paissan 8 shared papers
• Maurizio Omologo 8 shared papers
• Pooneh Mousavi 8 shared papers
• Artem Ploujnikov 6 shared papers
• Salah Zaiem 6 shared papers
• Samuele Cornell 6 shared papers
• Fran\c{c}ois Grondin 5 shared papers
• Peter Plantinga 5 shared papers
• Yingzhi Wang 5 shared papers
• Loren Lugosch 4 shared papers
• Philemon Brakel 4 shared papers
• Renato De Mori 4 shared papers
• Shubham Gupta 4 shared papers
• Szu-Wei Fu 4 shared papers
• Cheng Yu 3 shared papers
• Jarod Duret 3 shared papers