List your company

Research

Tasks

Explore the problems researchers are working on and the benchmarks used to measure progress.

2,225 tasksPage 58 of 89

Reset

Tasks

TaskDomainBenchmarksPapersLast update
Underwater Acoustic Classificationcomputer visionspeech audio12Apr 20, 2026
Audio-to-Motion Generationspeech audiocomputer vision11Feb 18, 2026
Self-supervised pretrainingspeech audio11Feb 19, 2026
System-level human MOS correlationspeech audio11Mar 25, 2026
Audio-to-video synthesisspeech audiovideo generation editing11Mar 25, 2026
Generalized Zero-Shot Retrieval (Text-to-Audio)retrieval search ragspeech audio+111Feb 18, 2026
Speech-driven 3D Holistic Body Motion Generationspeech audio3d vision geometry11Feb 18, 2026
Unified Audio and Video Generationvideo generation editingspeech audio11Mar 25, 2026
Audio-based Referring Video Object Segmentationcomputer visionspeech audio+111Mar 25, 2026
Audio-driven human animationspeech audiocomputer vision11Mar 25, 2026
Speech-to-speech response generationspeech audio11Mar 25, 2026
Target Speaker Trackingspeech audiocomputer vision11Mar 26, 2026
Audio-to-Text Classificationspeech audionlp11Mar 26, 2026
Generalized Zero-Shot Retrieval (Text-to-Audio-Video)retrieval search ragspeech audio+211Feb 18, 2026
5-speaker speech separationspeech audio11Feb 18, 2026
Voice Empathyspeech audionlp11Feb 19, 2026
Text-to-Audio Classificationspeech audionlp11Mar 26, 2026
Open QA (Speech to Text)speech audionlp11Feb 19, 2026
Speech Synthesis Quality Evaluation Correlation Analysisspeech audio11Mar 26, 2026
Audio-to-Text temporal groundingspeech audiocomputer vision11Feb 27, 2026
Text-to-Audio temporal groundingspeech audionlp+112Jul 7, 2026
Speech Evaluationspeech audio11Mar 27, 2026
Spoken command recognitionspeech audio12Feb 18, 2026
Video-to-Audio temporal groundingmultimodalspeech audio+112Jul 7, 2026
Hotword Retrievalretrieval search ragspeech audio11Mar 27, 2026