Research · Speech-to-Text
ASR Robustness Showcase
Benchmark and demonstration of automatic speech recognition robustness across noise, accents, and adversarial perturbations.
Open the source ↗Similar Audio & Speech releases
- NVIDIA Nemotron 3.5 Transcribe 30B-A4B
NVIDIA · Open multilingual ASR · Week 45, 2026
- Phonon-2
Fermion Research · Compressed English ASR · Week 41, 2026
- Hy-SimulMT
Tencent Hunyuan · Simultaneous speech translation · Week 45, 2026
- Who
Desert Ant Labs · On-device diarization · Week 45, 2026
- Dessa
Block (Dessa research lab) · Speech-only conversation model · Week 45, 2026
- Underdog Bark 3.0
Underdog · Speech Recognition · Week 44, 2026
More from Research
- ReactiveGWM
Research · Embodied AI · Week 21, 2026
- Flash-GRPO
Research · Text-to-Video · Week 21, 2026
- LiTo: Surface Light Field Tokenization
Research · 3D Reconstruction · Week 21, 2026
- FashionChameleon
Research · Image Editing · Week 21, 2026
- PanoWorld
Research · 3D Generation · Week 21, 2026
- WavFlow
Research · Music Generation · Week 21, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.