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 5 · SOTA2 Research
Back to Research
Research domain
Speech & Audio
Search tasks
Search
10 benchmarks · 6 papers
Multi-speaker Automatic Speech Recognition
10 benchmarks · 2 papers
Target-speaker Automatic Speech Recognition
10 benchmarks · 4 papers
Speaker Extraction
10 benchmarks · 6 papers
Singing Voice Conversion
10 benchmarks · 4 papers
Speech-to-Text
10 benchmarks · 18 papers
Audio-Visual Classification
10 benchmarks · 4 papers
Referring Audio-Visual Segmentation
10 benchmarks · 1 papers
Target-Speaker Multilingual Speech Generation
10 benchmarks · 4 papers
Audio Description Generation
10 benchmarks · 8 papers
Speech Quality Evaluation
10 benchmarks · 4 papers
Speech Bandwidth Extension
10 benchmarks · 2 papers
EEG Denoising
10 benchmarks · 6 papers
Speaker Similarity
10 benchmarks · 1 papers
ASR Accent Adaptation
10 benchmarks · 2 papers
Audio Watermark Detection
10 benchmarks · 1 papers
Binomial test for accent bias
9 benchmarks · 1 papers
Speech Watermarking
9 benchmarks · 10 papers
Audio-to-Video Retrieval
9 benchmarks · 8 papers
Joint audio-video generation
9 benchmarks · 6 papers
Video-to-Speech Synthesis
9 benchmarks · 8 papers
Automated Speech Recognition
9 benchmarks · 1 papers
Automatic Subtitling
9 benchmarks · 4 papers
Emotional Speech Synthesis
9 benchmarks · 4 papers
Subjective Evaluation
9 benchmarks · 5 papers
ASR rescoring
9 benchmarks · 1 papers
Music Restoration
9 benchmarks · 1 papers
Speech Alignment
9 benchmarks · 1 papers
Respiratory audio classification
9 benchmarks · 4 papers
Neural Audio Compression
9 benchmarks · 3 papers
Environmental Sound Deepfake Detection
9 benchmarks · 10 papers
Speech Dereverberation
9 benchmarks · 1 papers
Pathological speech intelligibility assessment
Page 5 of 70
Previous
Next