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 76–100 of 270 papers

TitleStatusHype
Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio GenerationCode0
SNAC: Multi-Scale Neural Audio CodecCode4
Movie Gen: A Cast of Media Foundation ModelsCode3
FlashAudio: Rectified Flows for Fast and High-Fidelity Text-to-Audio GenerationCode5
Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation—0
Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection—0
Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition—0
MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation—0
Analyzing and Mitigating Inconsistency in Discrete Audio Tokens for Neural Codec Language Models—0
From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and GenerationCode1
ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and SpeechCode3
Video-to-Audio Generation with Fine-grained Temporal Semantics—0
Temporally Aligned Audio for Video with AutoregressionCode1
PTQ4ADM: Post-Training Quantization for Efficient Text Conditional Audio Diffusion Models—0
NDVQ: Robust Neural Audio Codec with Normal Distribution-Based Vector Quantization—0
AudioComposer: Towards Fine-grained Audio Generation with Natural Language Descriptions—0
EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer—0
Learning Source Disentanglement in Neural Audio Codec—0
Text Prompt is Not Enough: Sound Event Enhanced Prompt Adapter for Target Style Audio Generation—0
TSELM: Target Speaker Extraction using Discrete Tokens and Language ModelsCode2
MetaBGM: Dynamic Soundtrack Transformation For Continuous Multi-Scene Experiences With Ambient Awareness And Personalization—0
Applications and Advances of Artificial Intelligence in Music Generation:A Review—0
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language ModelCode3
Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound—0
Demystifying the Communication Characteristics for Distributed Transformer Models—0
Show:102550
← PrevPage 4 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