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 26–50 of 270 papers

TitleStatusHype
Language-Codec: Bridging Discrete Codec Representations and Speech Language ModelsCode3
Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion ModelCode3
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language ModelCode3
BigVGAN: A Universal Neural Vocoder with Large-Scale TrainingCode3
OmniAudio: Generating Spatial Audio from 360-Degree VideoCode3
Gotta Hear Them All: Sound Source Aware Vision to Audio GenerationCode2
Generative Pre-trained Speech Language Model with Efficient Hierarchical TransformerCode2
Taming Data and Transformers for Audio GenerationCode2
Baichuan-Omni-1.5 Technical ReportCode2
RFWave: Multi-band Rectified Flow for Audio Waveform ReconstructionCode2
SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial SoundCode2
SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound GenerationCode2
Symphony Generation with Permutation Invariant Language ModelCode2
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial NetworksCode2
ETTA: Elucidating the Design Space of Text-to-Audio ModelsCode2
Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio GenerationCode2
Diffsound: Discrete Diffusion Model for Text-to-sound GenerationCode2
Efficient Autoregressive Audio Modeling via Next-Scale PredictionCode2
Audio Deepfake Detection with Self-Supervised XLS-R and SLS ClassifierCode2
PodAgent: A Comprehensive Framework for Podcast GenerationCode2
Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow MatchingCode2
DDSP: Differentiable Digital Signal ProcessingCode2
RingFormer: A Neural Vocoder with Ring Attention and Convolution-Augmented TransformerCode2
KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio GenerationCode2
Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion ModelsCode2
Show:102550
← PrevPage 2 of 11Next →
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