PlanAudio introduces a unified autoregressive LLM framework with semantic latent chain-of-thought for generating composite speech and sound audio from free-form text, plus a new benchmark.
hub
Gemmeke, Daniel P
9 Pith papers cite this work, alongside 2,979 external citations. Polarity classification is still indexing.
9
Pith papers citing it
2,979
external citations · external index
hub tools
representative citing papers
CleanCodec reframes audio tokenization as a selective information bottleneck to encode only perceptually important features at 12.5 tokens per second, outperforming prior codecs in efficiency, speaker similarity, and intelligibility.
A parameter-efficient dual-encoder model with differentiable Choquet integral fusion improves underwater acoustic classification accuracy over single-encoder baselines on DeepShip and ShipsEar datasets.
A smartwatch system detected social interactions in daily life with 77% of its alerts confirmed by users, and a multi-sensor model reached 90% balanced accuracy on 15-second windows.
Step-Audio 2 integrates a latent audio encoder, reasoning-centric reinforcement learning, and discrete audio token generation into language modeling to deliver state-of-the-art performance on audio understanding and conversational benchmarks.
MAP-Elites with CPPNs, DSP graphs, and a deep classifier produces diverse synthetic sounds across durations and musical/non-musical contexts.
MAPO is a dual-branch RL framework using modality relevance masks from cross-modal differential entropy and auxiliary attention losses to reduce late-stage modality collapse in audio reasoning models and improve benchmark results.
EntangleCodec unifies semantic and acoustic audio tokenization via caption alignment and flow-matching decoding, reporting competitive reconstruction, +7.4% gains on MMAR understanding, and 0.6B-parameter ALMs surpassing 13B-parameter continuous baselines.
Pretraining on broad sound events plus on-the-fly augmentations improves out-of-domain true-positive rates for acoustic drone detection at fixed low false-positive rates.
citing papers explorer
-
Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts
PlanAudio introduces a unified autoregressive LLM framework with semantic latent chain-of-thought for generating composite speech and sound audio from free-form text, plus a new benchmark.
-
CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding
CleanCodec reframes audio tokenization as a selective information bottleneck to encode only perceptually important features at 12.5 tokens per second, outperforming prior codecs in efficiency, speaker similarity, and intelligibility.
-
Parameter-efficient Dual-encoder Architecture with Differentiable Choquet Integral Fusion for Underwater Acoustic Classification
A parameter-efficient dual-encoder model with differentiable Choquet integral fusion improves underwater acoustic classification accuracy over single-encoder baselines on DeepShip and ShipsEar datasets.
-
SocialPulse: On-Device Detection of Social Interactions in Naturalistic Settings Using Smartwatch Sensing
A smartwatch system detected social interactions in daily life with 77% of its alerts confirmed by users, and a multi-sensor model reached 90% balanced accuracy on 15-second windows.
-
Step-Audio 2 Technical Report
Step-Audio 2 integrates a latent audio encoder, reasoning-centric reinforcement learning, and discrete audio token generation into language modeling to deliver state-of-the-art performance on audio understanding and conversational benchmarks.
-
Quality-Diversity Search in Sound Generation: Investigating Innovation Engines for Audio Exploration
MAP-Elites with CPPNs, DSP graphs, and a deep classifier produces diverse synthetic sounds across durations and musical/non-musical contexts.
-
Escape the Language Prior: Mitigating Late-Stage Modality Collapse in Audio Reasoning via Modality-Aware Policy Optimization
MAPO is a dual-branch RL framework using modality relevance masks from cross-modal differential entropy and auxiliary attention losses to reduce late-stage modality collapse in audio reasoning models and improve benchmark results.
-
EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement
EntangleCodec unifies semantic and acoustic audio tokenization via caption alignment and flow-matching decoding, reporting competitive reconstruction, +7.4% gains on MMAR understanding, and 0.6B-parameter ALMs surpassing 13B-parameter continuous baselines.
-
Improving acoustic drone detection generalization through pretraining and data augmentation
Pretraining on broad sound events plus on-the-fly augmentations improves out-of-domain true-positive rates for acoustic drone detection at fixed low false-positive rates.