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 41 · SOTA2 Research

Back to Research

Research domain

Speech & Audio

Search tasks

1 benchmarks · 1 papersUniversal Neural Vocoding 1 benchmarks · 2 papersAudio-to-video generation (A2V)1 benchmarks · 1 papersBeats-controlled Audio Generation 1 benchmarks · 1 papersBeats+Intensity-controlled Audio Generation 1 benchmarks · 1 papersPitch-controlled Audio Generation 1 benchmarks · 1 papersPitch+Intensity-controlled Audio Generation 1 benchmarks · 1 papersIntensity-controlled Audio Generation 1 benchmarks · 1 papersAudio-Text 1 benchmarks · 1 papersSinging Lyric Editing 1 benchmarks · 1 papersAcoustic Evaluation 1 benchmarks · 1 papersVoice Type Classification 1 benchmarks · 1 papersVoice Timbre Analysis and Discrimination

1 benchmarks · 1 papersAuditory Reasoning

1 benchmarks · 1 papersAcoustic and paralinguistic modeling

1 benchmarks · 1 papersSpoken Dialogue State Tracking

1 benchmarks · 1 papersSpeechLM-based Text-to-Speech

1 benchmarks · 1 papersEmotion and speaker adaptation

1 benchmarks · 1 papersInference speed estimation

1 benchmarks · 1 papersProbabilistic audio geolocation

1 benchmarks · 1 papersMalicious Speech Classification

1 benchmarks · 1 papersFake Speech Detection

1 benchmarks · 1 papersTranscription Prediction

1 benchmarks · 1 papersSpeech reconstruction via differential pressure sensors

1 benchmarks · 1 papersAudio-Visual Joint Reasoning

1 benchmarks · 1 papersAudio-Visual Speaker Identification

1 benchmarks · 1 papersAudio Multiple-Choice Question Answering

1 benchmarks · 1 papersSounding Object Localization

1 benchmarks · 1 papersClose-ended Spoken Question Answering

1 benchmarks · 1 papersAudio-driven face reenactment

1 benchmarks · 1 papersJoint Audio-Visual Generation

1 benchmarks · 1 papersAudio Bandwidth Extension (8→48 kHz)

1 benchmarks · 1 papersStreaming Speech Generation

Page 41 of 70