Miloš Cerňak

Logitech (Switzerland) — Switzerland

Computer Science · Physical Sciences

16h-index850citations115works0.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(78), Speech and Audio Processing(72), Music and Audio Processing(48), Phonetics and Phonology Research(25), Advanced Data Compression Techniques(14)

Publications115 total

Shortcut Flow Matching for Speech Enhancement: Step-Invariant flows via single stage training
arXiv (Cornell University)·2025Open Access
Low-latency Assistive Audio Enhancement for Neurodivergent People
arXiv (Cornell University)·2025Open Access
Model as Loss: A Self-Consistent Training Paradigm
2025
DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration
2025Open Access
DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration
arXiv (Cornell University)·2025Open Access
Model as Loss: A Self-Consistent Training Paradigm
arXiv (Cornell University)·2025Open Access
OpenACE: An Open Benchmark for Evaluating Audio Coding Performance
2025
Semi-intrusive audio evaluation: Casting non-intrusive assessment as a multi-modal text prediction task
arXiv (Cornell University)·2024Open Access
OpenACE: An Open Benchmark for Evaluating Audio Coding Performance
arXiv (Cornell University)·2024Open Access
Diffusion-based Speech Enhancement with Schrödinger Bridge and Symmetric Noise Schedule
arXiv (Cornell University)·2024Open Access
Multi-Channel Mosra: Mean Opinion Score and Room Acoustics Estimation Using Simulated Data and A Teacher Model
2024· 1 cited
On Real-Time Multi-Stage Speech Enhancement Systems
2024· 1 citedOpen Access
On real-time multi-stage speech enhancement systems
arXiv (Cornell University)·2023Open Access
Multi-Channel MOSRA: Mean Opinion Score and Room Acoustics Estimation Using Simulated Data and a Teacher Model
arXiv (Cornell University)·2023Open Access
Cluster-based pruning techniques for audio data
arXiv (Cornell University)·2023· 1 citedOpen Access
Speaker Embeddings as Individuality Proxy for Voice Stress Detection
2023· 3 cited
ALO-VC: Any-to-any Low-latency One-shot Voice Conversion
2023· 1 cited
Speaker Embeddings as Individuality Proxy for Voice Stress Detection
arXiv (Cornell University)·2023Open Access
ALO-VC: Any-to-any Low-latency One-shot Voice Conversion
arXiv (Cornell University)·2023Open Access
Personalized Task Load Prediction in Speech Communication
2023· 2 cited
page 1 of 6Next →

Frequent Co-authors

Philip N. Garner(10), Afsaneh Asaei(7), Petr Motlíček(5), Mikolaj Kegler(5), Pierre Beckmann(5), Juan Rafael Orozco‐Arroyave(4), Elmar Nöth(4), Marián Trnka(4), Milan Rusko(4), Hervé Bourlard(4), Juan Camilo Vásquez-Correa(3), Sakhia Darjaa(3), Pablo Mainar(3), Frank Rudzicz(2), Heidi Christensen(2), Róbert Sabo(2), Alexandros Lazaridis(2), Neil Scheidwasser(2), Flavio Martinelli(2), Giorgia Dellaferrera(2)