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 10 · SOTA2 Research

Back to Research

Research domain

Speech & Audio

Search tasks

5 benchmarks · 1 papersTurn-detection 5 benchmarks · 3 papersAudio-driven Avatar Generation 5 benchmarks · 2 papersMulti-channel Speech Separation 5 benchmarks · 2 papersPhoneme Classification 5 benchmarks · 1 papersAuthentication Restoration 5 benchmarks · 1 papersLong speech understanding and reasoning 5 benchmarks · 1 papersTimbre-agnostic transcription 5 benchmarks · 1 papersTimbre-separated transcription 5 benchmarks · 3 papersSpeech Decoding 5 benchmarks · 1 papersASR Attack 5 benchmarks · 1 papersSpeech Function Calling 5 benchmarks · 2 papersMonaural Speech Separation

5 benchmarks · 1 papers

Audio-to-Text Chat

5 benchmarks · 2 papersSpoken dialogue generation

5 benchmarks · 2 papersNoise Suppression

5 benchmarks · 3 papersVocoding

5 benchmarks · 1 papersAudio-Visual Automatic Speech Recognition

5 benchmarks · 1 papersPost-ASR Entity Correction

5 benchmarks · 1 papersBinary classification (Human vs Machine speech)

5 benchmarks · 2 papersSpeech Intelligibility Assessment

5 benchmarks · 5 papersSpoken Language Modeling

5 benchmarks · 3 papersLip-syncing

5 benchmarks · 4 papersSpoof detection

5 benchmarks · 5 papersAudio event classification

5 benchmarks · 1 papersMedical Audio Analysis

5 benchmarks · 4 papersAudio Quality Evaluation

5 benchmarks · 1 papersSource Counting

5 benchmarks · 4 papersAudiovisual Understanding & Reasoning

5 benchmarks · 1 papersIn-context Text-to-Speech

5 benchmarks · 2 papersAudio Inpainting

5 benchmarks · 3 papersPacket Loss Concealment

5 benchmarks · 2 papersWiFi-based Gesture Recognition

Page 10 of 70