Categories
Companies
Research
Sign in
Join
Loading the SOTA2 catalog…
WizWand is now SOTA2 Research
SOTA2
Research
Papers
Benchmarks
Datasets
Tasks
Speech & Audio AI research – Page 2 · SOTA2 Research
Back to Research
Research domain
Speech & Audio
Search tasks
Search
36 benchmarks · 18 papers
Target Speaker Extraction
34 benchmarks · 16 papers
Active Speaker Detection
34 benchmarks · 47 papers
Audio Captioning
33 benchmarks · 7 papers
Audio Watermarking
32 benchmarks · 10 papers
Audio Super-Resolution
31 benchmarks · 25 papers
Sound Event Detection
31 benchmarks · 13 papers
Source Separation
30 benchmarks · 14 papers
Speech Deepfake Detection
30 benchmarks · 15 papers
Zero-shot Text-to-Speech
30 benchmarks · 12 papers
Respiratory sound classification
30 benchmarks · 24 papers
Visual Speech Recognition
30 benchmarks · 30 papers
Speaker Identification
30 benchmarks · 10 papers
ASR Error Correction
29 benchmarks · 21 papers
Audio-to-Text Retrieval
29 benchmarks · 14 papers
Isolated Sign Language Recognition
28 benchmarks · 47 papers
Text-to-Audio Generation
27 benchmarks · 23 papers
Phoneme Recognition
27 benchmarks · 23 papers
Environmental Sound Classification
25 benchmarks · 7 papers
Multi-talker Automatic Speech Recognition
24 benchmarks · 19 papers
Continuous Sign Language Recognition
23 benchmarks · 33 papers
Video-to-Audio Generation
23 benchmarks · 5 papers
Arousal classification
23 benchmarks · 8 papers
Speaker-attributed Automatic Speech Recognition
23 benchmarks · 19 papers
Speech Classification
22 benchmarks · 5 papers
Anomalous Sound Detection
22 benchmarks · 10 papers
Speech Question Answering
21 benchmarks · 6 papers
Source Localization
20 benchmarks · 8 papers
Audio Editing
19 benchmarks · 6 papers
Speech Restoration
19 benchmarks · 11 papers
Voice Cloning
19 benchmarks · 15 papers
Speech Generation
18 benchmarks · 3 papers
Simultaneous Speech-to-Speech Translation
Page 2 of 70
Previous
Next