NAVA proposes native audio-visual alignment via Align-then-Fuse MMDiT and Timbre-in-Context Conditioning for joint audio-video generation with improved synchronization and timbre control.
hub Canonical reference
Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound
Canonical reference. 80% of citing Pith papers cite this work as background.
29
Pith papers citing it
Background
80% of classified citations
abstract
The quantification of audio aesthetics remains a complex challenge in audio processing, primarily due to its subjective nature, which is influenced by human perception and cultural context. Traditional methods often depend on human listeners for evaluation, leading to inconsistencies and high resource demands. This paper addresses the growing need for automated systems capable of predicting audio aesthetics without human intervention. Such systems are crucial for applications like data filtering, pseudo-labeling large datasets, and evaluating generative audio models, especially as these models become more sophisticated. In this work, we introduce a novel approach to audio aesthetic evaluation by proposing new annotation guidelines that decompose human listening perspectives into four distinct axes. We develop and train no-reference, per-item prediction models that offer a more nuanced assessment of audio quality. Our models are evaluated against human mean opinion scores (MOS) and existing methods, demonstrating comparable or superior performance. This research not only advances the field of audio aesthetics but also provides open-source models and datasets to facilitate future work and benchmarking. We release our code and pre-trained model at: https://github.com/facebookresearch/audiobox-aesthetics
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
representative citing papers
InstructAV2AV is an end-to-end instruction-guided audio-video joint editing model that adapts a pre-trained backbone with gated attention and two-stage training, outperforming prior methods on 11 metrics after building the InsAVE-80K dataset.
BandTok tokenizes Mel-spectrograms as independent time-frequency band tokens from a single codebook and pairs it with 2D RoPE in an autoregressive model to improve music generation over residual multi-codebook tokenizers.
OmniNFT introduces modality-wise advantage routing, layer-wise gradient surgery, and region-wise loss reweighting in an online diffusion RL framework to improve audio-video quality, alignment, and synchronization.
TMD-Bench is a multi-level benchmark that measures music-dance co-generation quality including beat-level rhythmic synchronization, supported by a new dataset and Music Captioner, and shows commercial models lag in rhythm while a new baseline performs competitively.
Hallo-Live achieves 20.38 FPS real-time text-to-audio-video avatar generation with 0.94s latency using asynchronous dual-stream diffusion and HP-DMD preference distillation, matching teacher model quality at 16x higher throughput.
VidAudio-Bench benchmarks V2A and VT2A models across four audio categories, revealing poor speech/singing performance and a tension between visual alignment and text instruction following.
MIDI-SAG generates consistent long-form singing accompaniments by feeding symbolic MIDI timing, chords, and structure labels into a compositional pipeline built from pre-trained modules.
A single DiT-based diffusion model unifies video-to-audio, text-to-audio, and joint video-text-to-audio generation, supported by a new 470k-pair dataset and three-stage progressive training that resolves task competition.
AVI-Edit enables precise audio-synchronized instance-level video editing via a granularity-aware mask refiner, a self-feedback audio agent, and a new large-scale annotated dataset.
VABench is a new multi-dimensional benchmark for evaluating synchronous audio-video generation across text-to-AV, image-to-AV, and stereo tasks.
AudioRole provides 1M+ character-grounded audio-text dialogues from TV series plus ARP-Eval to train and measure audio role-playing models, with ARP-Model showing 0.31 acoustic and 0.36 content personalization scores.
Libretto is a new agent-facing symbolic music framework that equips LLMs with explicit grammar and corpus-calibrated statistical axes to enable measurable generation, gap-filling, morphing, and self-revision.
WavFlow performs direct waveform audio generation via flow matching on 2D token grids from raw patches plus amplitude lifting, matching latent-based methods on VGGSound and AudioCaps without intermediate compression.
A curation pipeline combining diffusion-based synthetic mixtures with a discriminative classifier produces and releases FSD50K-Solo, a single-source subset of FSD50K that matches human expert labels on a test set.
VocalParse applies interleaved and Chain-of-Thought prompting to a Large Audio Language Model to jointly transcribe lyrics, melody and word-note alignments, achieving state-of-the-art results on multiple singing datasets.
JASTIN is an instruction-driven audio evaluation system that achieves state-of-the-art correlation with human ratings on speech, sound, music, and out-of-domain tasks without task-specific retraining.
APEX jointly predicts popularity and aesthetic quality for AI-generated music from MERT embeddings and shows that aesthetic features improve human preference prediction on unseen generative systems.
SongBench is a new fine-grained benchmark for song quality assessment with seven dimensions and an expert-annotated dataset of 11,717 samples showing high correlation with professional ratings.
SA-SLM uses variational information bottleneck for intent-aware bridging and self-criticism for realization-aware alignment to close the semantic-acoustic gap, outperforming open-source models and nearing GPT-4o-Audio expressiveness on EchoMind after training on 800 hours of data.
Activation steering at a semantic bottleneck in audio diffusion models achieves state-of-the-art control over musical attributes such as instruments, vocals, and genres.
LAION-Aesthetics Predictor reinforces Western and male biases by preferentially selecting images associated with women and realistic Western/Japanese art while excluding men, LGBTQ+ references, and other styles.
DreamAudio generates audio clips that incorporate user-specified personalized audio events from reference samples while remaining aligned with text prompts.
SonicMaster is a text-conditioned flow-matching generative model for unified music restoration and mastering, trained on a dataset of simulated degradations across equalization, dynamics, reverb, amplitude, and stereo.
citing papers explorer
-
Native Audio-Visual Alignment for Generation
NAVA proposes native audio-visual alignment via Align-then-Fuse MMDiT and Timbre-in-Context Conditioning for joint audio-video generation with improved synchronization and timbre control.
-
InstructAV2AV: Instruction-Guided Audio-Video Joint Editing
InstructAV2AV is an end-to-end instruction-guided audio-video joint editing model that adapts a pre-trained backbone with gated attention and two-stage training, outperforming prior methods on 11 metrics after building the InsAVE-80K dataset.
-
Modeling Music as a Time-Frequency Image: A 2D Tokenizer for Music Generation
BandTok tokenizes Mel-spectrograms as independent time-frequency band tokens from a single codebook and pairs it with 2D RoPE in an autoregressive model to improve music generation over residual multi-codebook tokenizers.
-
OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
OmniNFT introduces modality-wise advantage routing, layer-wise gradient surgery, and region-wise loss reweighting in an online diffusion RL framework to improve audio-video quality, alignment, and synchronization.
-
TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation
TMD-Bench is a multi-level benchmark that measures music-dance co-generation quality including beat-level rhythmic synchronization, supported by a new dataset and Music Captioner, and shows commercial models lag in rhythm while a new baseline performs competitively.
-
Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation
Hallo-Live achieves 20.38 FPS real-time text-to-audio-video avatar generation with 0.94s latency using asynchronous dual-stream diffusion and HP-DMD preference distillation, matching teacher model quality at 16x higher throughput.
-
VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories
VidAudio-Bench benchmarks V2A and VT2A models across four audio categories, revealing poor speech/singing performance and a tension between visual alignment and text instruction following.
-
MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline
MIDI-SAG generates consistent long-form singing accompaniments by feeding symbolic MIDI timing, chords, and structure labels into a compositional pipeline built from pre-trained modules.
-
Omni2Sound: Towards Unified Video-Text-to-Audio Generation
A single DiT-based diffusion model unifies video-to-audio, text-to-audio, and joint video-text-to-audio generation, supported by a new 470k-pair dataset and three-stage progressive training that resolves task competition.
-
AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner
AVI-Edit enables precise audio-synchronized instance-level video editing via a granularity-aware mask refiner, a self-feedback audio agent, and a new large-scale annotated dataset.
-
VABench: A Comprehensive Benchmark for Audio-Video Generation
VABench is a new multi-dimensional benchmark for evaluating synchronous audio-video generation across text-to-AV, image-to-AV, and stereo tasks.
-
AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models
AudioRole provides 1M+ character-grounded audio-text dialogues from TV series plus ARP-Eval to train and measure audio role-playing models, with ARP-Model showing 0.31 acoustic and 0.36 content personalization scores.
-
Libretto: Giving LLM Agents a Sense of Musical Structure
Libretto is a new agent-facing symbolic music framework that equips LLMs with explicit grammar and corpus-calibrated statistical axes to enable measurable generation, gap-filling, morphing, and self-revision.
-
WavFlow: Audio Generation in Waveform Space
WavFlow performs direct waveform audio generation via flow matching on 2D token grids from raw patches plus amplitude lifting, matching latent-based methods on VGGSound and AudioCaps without intermediate compression.
-
FSD50K-Solo: Automated Curation of Single-Source Sound Events
A curation pipeline combining diffusion-based synthetic mixtures with a discriminative classifier produces and releases FSD50K-Solo, a single-source subset of FSD50K that matches human expert labels on a test set.
-
VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Models
VocalParse applies interleaved and Chain-of-Thought prompting to a Large Audio Language Model to jointly transcribe lyrics, melody and word-note alignments, achieving state-of-the-art results on multiple singing datasets.
-
JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions
JASTIN is an instruction-driven audio evaluation system that achieves state-of-the-art correlation with human ratings on speech, sound, music, and out-of-domain tasks without task-specific retraining.
-
APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music
APEX jointly predicts popularity and aesthetic quality for AI-generated music from MERT embeddings and shows that aesthetic features improve human preference prediction on unseen generative systems.
-
SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment
SongBench is a new fine-grained benchmark for song quality assessment with seven dimensions and an expert-annotated dataset of 11,717 samples showing high correlation with professional ratings.
-
Bridging What the Model Thinks and How It Speaks: Self-Aware Speech Language Models for Expressive Speech Generation
SA-SLM uses variational information bottleneck for intent-aware bridging and self-criticism for realization-aware alignment to close the semantic-acoustic gap, outperforming open-source models and nearing GPT-4o-Audio expressiveness on EchoMind after training on 800 hours of data.
-
TADA! Tuning Audio Diffusion Models through Activation Steering
Activation steering at a semantic bottleneck in audio diffusion models achieves state-of-the-art control over musical attributes such as instruments, vocals, and genres.
-
The Algorithmic Gaze of Image Quality Assessment: An Audit and Trace Ethnography of the LAION-Aesthetics Predictor
LAION-Aesthetics Predictor reinforces Western and male biases by preferentially selecting images associated with women and realistic Western/Japanese art while excluding men, LGBTQ+ references, and other styles.
-
DreamAudio: Customized Text-to-Audio Generation with Diffusion Models
DreamAudio generates audio clips that incorporate user-specified personalized audio events from reference samples while remaining aligned with text prompts.
-
SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
SonicMaster is a text-conditioned flow-matching generative model for unified music restoration and mastering, trained on a dataset of simulated degradations across equalization, dynamics, reverb, amplitude, and stereo.
-
Instrumental Text-to-Music Generation with Auxiliary Conditioning Branches
Auxiliary lyric and timbre branches improve instrumental text-to-music generation quality in a controlled DiT setting even with degenerate inputs, outperforming parameter-reallocated depth variants and external baselines in objective and MOS evaluations.
-
AuDirector: A Self-Reflective Closed-Loop Framework for Immersive Audio Storytelling
AuDirector proposes a self-reflective closed-loop multi-agent framework with identity-aware pre-production, collaborative synthesis-correction, and human-guided refinement for coherent immersive audio storytelling.
-
Scaling Properties of Continuous Diffusion Spoken Language Models
Continuous diffusion spoken language models follow scaling laws for loss and phoneme divergence and generate emotive multi-speaker speech at 16B scale, though long-form coherence stays difficult.
-
MAVIN: Multi-Shot Audio-Visual Generation with Narrative Control
MAVIN proposes boundary-aware attention, ID-aware propagation, a multi-agent scripting pipeline, and the MAVINSet dataset as the first framework for multi-shot audio-visual generation with narrative control, claiming SOTA results.
- OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation