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 32 · SOTA2 Research
Back to Research
Research domain
Speech & Audio
Search tasks
Search
2 benchmarks · 1 papers
Note-level Singing Voice Transcription
2 benchmarks · 1 papers
Video Background Music Generation
2 benchmarks · 2 papers
Human Recognition
2 benchmarks · 1 papers
Audio Time-Stretching
2 benchmarks · 2 papers
Alzheimer's Disease Recognition from Speech
2 benchmarks · 1 papers
Speech-to-Singing conversion
2 benchmarks · 1 papers
Speech Semantic Understanding
2 benchmarks · 1 papers
Time-stretching
2 benchmarks · 1 papers
Linear correlation between human MOS and automatic metrics
2 benchmarks · 1 papers
Style Prompt Adherence evaluation
2 benchmarks · 1 papers
ASV Spoofing Detection
2 benchmarks · 1 papers
Speaking Speed Control
2 benchmarks · 1 papers
Text-Only Speech Synthesis
2 benchmarks · 1 papers
Subjective Speech Evaluation Prediction
2 benchmarks · 1 papers
Video-Audio Question Answering
2 benchmarks · 1 papers
System naturalness prediction
2 benchmarks · 1 papers
Artwork-to-Music Generation
2 benchmarks · 1 papers
Fingerspelling Word Search (Video to Text)
2 benchmarks · 1 papers
Spoken Language Glossification
2 benchmarks · 1 papers
Text-audio retrieval
2 benchmarks · 1 papers
Multi-speaker Voice Clone
2 benchmarks · 1 papers
Dialect Synthesis
2 benchmarks · 1 papers
Named Entity Correction
2 benchmarks · 1 papers
Acoustic Word Discrimination
2 benchmarks · 1 papers
Controllable Speech Synthesis
2 benchmarks · 1 papers
Symbolic Music Emotion Recognition
2 benchmarks · 1 papers
TTS Quality Improvement
2 benchmarks · 1 papers
Image Guided Audio Temporal Localization
2 benchmarks · 2 papers
Speech Naturalness Evaluation
2 benchmarks · 1 papers
Speech Activity Detection
2 benchmarks · 1 papers
Multi-speaker Dubbing
2 benchmarks · 3 papers
Single-source sound localization
Page 32 of 70
Previous
Next