SOTAVerified

Audio Generation

Audio generation (synthesis) is the task of generating raw audio such as speech.

( Image credit: MelNet )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 270 papers

TitleStatusHype
FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation—0
ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and EditingCode5
Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance—0
Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation—0
ViSAGe: Video-to-Spatial Audio Generation—0
LiLAC: A Lightweight Latent ControlNet for Musical Audio Generation—0
BemaGANv2: A Tutorial and Comparative Survey of GAN-based Vocoders for Long-Term Audio GenerationCode1
A Survey of Automatic Evaluation Methods on Text, Visual and Speech Generations—0
Sounding that Object: Interactive Object-Aware Image to Audio Generation—0
InfiniteAudio: Infinite-Length Audio Generation with Consistency—0
DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization—0
XMAD-Bench: Cross-Domain Multilingual Audio Deepfake BenchmarkCode0
IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling—0
AudioTurbo: Fast Text-to-Audio Generation with Rectified Diffusion—0
Conditional Diffusion Models with Classifier-Free Gibbs-like GuidanceCode0
EnvSDD: Benchmarking Environmental Sound Deepfake Detection—0
MMMG: a Comprehensive and Reliable Evaluation Suite for Multitask Multimodal Generation—0
Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audio—0
DPN-GAN: Inducing Periodic Activations in Generative Adversarial Networks for High-Fidelity Audio Synthesis—0
Fast Text-to-Audio Generation with Adversarial Post-TrainingCode7
TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining—0
Discrete Optimal Transport and Voice Conversion—0
Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients—0
OmniAudio: Generating Spatial Audio from 360-Degree VideoCode3
On the Design of Diffusion-based Neural Speech Codecs—0
Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory PerceptionCode1
Multimodal Cinematic Video Synthesis Using Text-to-Image and Audio Generation Models—0
Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference OptimizationCode1
DeepSound-V1: Start to Think Step-by-Step in the Audio Generation from Videos—0
DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation—0
Make Some Noise: Towards LLM audio reasoning and generation using sound tokens—0
DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap—0
AudioX: Diffusion Transformer for Anything-to-Audio Generation—0
TA-V2A: Textually Assisted Video-to-Audio Generation—0
Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition—0
ReelWave: Multi-Agentic Movie Sound Generation through Multimodal LLM Conversation—0
Speech Audio Generation from dynamic MRI via a Knowledge Enhanced Conditional Variational Autoencoder—0
PodAgent: A Comprehensive Framework for Podcast GenerationCode2
InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music GenerationCode5
DualSpec: Text-to-spatial-audio Generation via Dual-Spectrogram Guided Diffusion Model—0
KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio GenerationCode2
Towards efficient quantum algorithms for diffusion probability models—0
AudioSpa: Spatializing Sound Events with Text—0
TokenSynth: A Token-based Neural Synthesizer for Instrument Cloning and Text-to-InstrumentCode2
Latent Swap Joint Diffusion for 2D Long-Form Latent GenerationCode4
ADIFF: Explaining audio difference using natural languageCode1
UniForm: A Unified Multi-Task Diffusion Transformer for Audio-Video Generation—0
AudioGenX: Explainability on Text-to-Audio Generative ModelsCode0
CosyAudio: Improving Audio Generation with Confidence Scores and Synthetic Captions—0
Baichuan-Omni-1.5 Technical ReportCode2
Show:102550
← PrevPage 1 of 6Next →
All datasetsAudioCapsClassical music, 5 seconds at 12 kHzSymphony music

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AudioGenFD_openl3185.53—Unverified
2AudioLDM2-largeFD_openl3158.04—Unverified
3Stable Audio 2.0FD_openl3110.62—Unverified
4Stable AudioFD_openl3103.66—Unverified
5ETTAFD_openl380.13—Unverified
6TangoFlux-baseFD_openl379.7—Unverified
7Stable Audio OpenFD_openl378.24—Unverified
8TangoFluxFD_openl375.1—Unverified
9ETTA-FT-AC-100kFD_openl361.79—Unverified
10DiffsoundFAD7.75—Unverified
#ModelMetricClaimedVerifiedStatus
1VAB-Encodec (Ours)Bits per byte40—Unverified
2Sparse Transformer 152M (strided)Bits per byte1.97—Unverified
#ModelMetricClaimedVerifiedStatus
1SymphonyNet Human listening average results3.5—Unverified