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 1–25 of 270 papers

TitleStatusHype
Long-form music generation with latent diffusionCode7
Fast Text-to-Audio Generation with Adversarial Post-TrainingCode7
Stable Audio OpenCode7
AudioLM: a Language Modeling Approach to Audio GenerationCode7
Fast Timing-Conditioned Latent Audio DiffusionCode7
MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio SynthesisCode7
SoundStorm: Efficient Parallel Audio GenerationCode6
AudioGen: Textually Guided Audio GenerationCode6
FlashAudio: Rectified Flows for Fast and High-Fidelity Text-to-Audio GenerationCode5
Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference OptimizationCode5
ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and EditingCode5
Improving Text-To-Audio Models with Synthetic CaptionsCode5
AudioLCM: Text-to-Audio Generation with Latent Consistency ModelsCode5
InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music GenerationCode5
AudioLDM 2: Learning Holistic Audio Generation with Self-supervised PretrainingCode4
AudioLDM: Text-to-Audio Generation with Latent Diffusion ModelsCode4
SNAC: Multi-Scale Neural Audio CodecCode4
Latent Swap Joint Diffusion for 2D Long-Form Latent GenerationCode4
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference OptimizationCode4
ArchiSound: Audio Generation with DiffusionCode4
FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized SoundsCode4
Enhancing Suno's Bark Text-to-Speech Model: Addressing Limitations Through Meta's Encodec and Pre-Trained HubertCode4
ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and SpeechCode3
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language ModelCode3
Language-Codec: Bridging Discrete Codec Representations and Speech Language ModelsCode3
Show:102550
← PrevPage 1 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