Scholar
Jonathan Le Roux
Google Scholar ID: aUpxty8AAAAJ
MERL
Audio Signal Processing
Audio Source Separation
Machine Listening
Speech Recognition
Machine Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
12,237
H-index
47
i10-index
124
Publications
20
Co-authors
72
list available
Publications
14 items
Evaluating Inference-time Algorithms for Semantic Sound Scene Segmentation
2026
Cited
0
Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching
2026
Cited
0
Predictive-Generative Drift Decomposition for Speech Enhancement and Separation
2026
Cited
0
Velocity Potential Neural Field for Efficient Ambisonics Impulse Response Modeling
2026
Cited
0
Mind the Gap: Detecting Cluster Exits for Robust Local Density-Based Score Normalization in Anomalous Sound Detection
2026
Cited
0
O-EENC-SD: Efficient Online End-to-End Neural Clustering for Speaker Diarization
2025
Cited
0
Robot Confirmation Generation and Action Planning Using Long-context Q-Former Integrated with Multimodal LLM
2025
Cited
0
FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement
2025
Cited
0
Load more
Co-authors
17 total
John Hershey
Google (formerly MERL, IBM, MSR, UCSD)
Shinji Watanabe
Carnegie Mellon University
gordon wichern
MERL
Takaaki Hori
Apple
Hirokazu Kameoka
Senior Distinguished Researcher at NTT, Adjunct Associate Professor at NII
Nobutaka Ono
Professor, Tokyo Metropolitan University
Niko Moritz
Meta AI
Hakan Erdogan
Google
