Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Speech & Audio AI research – Page 14 · SOTA2 Research

Back to Research

Research domain

Speech & Audio

Search tasks

4 benchmarks · 1 papersAudio Language Modeling 4 benchmarks · 3 papersAudio-driven portrait animation 4 benchmarks · 2 papersSpeaker Localization 4 benchmarks · 1 papersForeground Speaker Diarization 4 benchmarks · 3 papersAudio-Visual Target Speaker Extraction 4 benchmarks · 4 papersMulti-task performance evaluation 4 benchmarks · 2 papersVisual Text-to-Speech 4 benchmarks · 2 papersEmotion Editing 4 benchmarks · 4 papersMispronunciation Detection 4 benchmarks · 1 papersTranscription Quality Evaluation 4 benchmarks · 3 papersMultimodal Audio Understanding 4 benchmarks · 6 papersSpoofing Attack Detection

4 benchmarks · 2 papers

Voice Pathology Detection

4 benchmarks · 1 papersSpeaker Erasure

4 benchmarks · 4 papersFake Detection

4 benchmarks · 1 papersStreaming Voice-Agent Interaction Efficiency

4 benchmarks · 1 papersAcoustic Communication

4 benchmarks · 1 papersUnsupervised Automatic Speech Recognition

4 benchmarks · 1 papersDescription-based speech generation

4 benchmarks · 2 papersMulti-track music generation

4 benchmarks · 1 papersDysarthric Speech Reconstruction

4 benchmarks · 1 papersFine-grained Score Accuracy

4 benchmarks · 2 papersArousal Detection

4 benchmarks · 5 papersJoint Video-Audio Generation

4 benchmarks · 1 papersSynthetic word detection

4 benchmarks · 5 papersMusic Reconstruction

4 benchmarks · 2 papersEEG-based Emotion Recognition

4 benchmarks · 2 papersSpeech Anti-Spoofing

4 benchmarks · 1 papersAudio Modeling

4 benchmarks · 1 papersAcoustic Emotion Recognition

4 benchmarks · 1 papersMyoelectric Gesture Recognition

4 benchmarks · 1 papersAudio Quality Assessment Correlation

Page 14 of 70