HiFi-HARP: A High-Fidelity 7th-Order Ambisonic Room Impulse Response Dataset
arxiv.org·1d
👂Psychoacoustics
Flag this post
Swift Sings: MDX-Net Vocal Splits and RVC Voice Conversion On-Device with ONNX/CoreML
web.navan.dev·1d
🎧Learned Audio
Flag this post
Taming Text-to-Sounding Video Generation via Advanced Modality Condition andInteraction
🧠Neural Compression
Flag this post
Can large audio language models understand child stuttering speech? speech summarization, and source separation
arxiv.org·1d
🎙️Whisper
Flag this post
Variational autoencoders stabilise TCN performance when classifying weakly labelled bioacoustics data: an interdisciplinary approach
arxiv.org·1d
🧠Learned Codecs
Flag this post
Frequency-Spatial Interaction Driven Network for Low-Light Image Enhancement
arxiv.org·2h
📊Rate-Distortion Theory
Flag this post
Enhanced Spectral Decomposition for High-Dimensional Bio-Signal Classification
🌈Spectral Methods
Flag this post
Compositional Bias Control in Large Language Models: Preference Learning Fails, Supervision Succeeds
arxiv.org·2h
🎛️Feed Filtering
Flag this post
LibriConvo: Simulating Conversations from Read Literature for ASR and Diarization
arxiv.org·2h
🎵Audio ML
Flag this post
Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing
arxiv.org·2h
🧠Machine Learning
Flag this post
How to Apply Powerful AI Audio Models to Real-World Applications
towardsdatascience.com·10h
🎵Audio ML
Flag this post
The Limits of Data Scaling: Sub-token Utilization and Acoustic Saturation in Multilingual ASR
arxiv.org·2h
🎙️Whisper
Flag this post
Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMS
arxiv.org·2h
🎵Audio ML
Flag this post
Poisson Flow Consistency Training
arxiv.org·2h
🧠Machine Learning
Flag this post
Region-Adaptive Learned Hierarchical Encoding for 3D Gaussian Splatting Data
arxiv.org·2h
🧠Learned Codecs
Flag this post
Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders
arxiv.org·2h
🧠Machine Learning
Flag this post
FAME: Fairness-aware Attention-modulated Video Editing
arxiv.org·2h
🧠Learned Codecs
Flag this post
RatioWaveNet: A Learnable RDWT Front-End for Robust and Interpretable EEG Motor-Imagery Classification
arxiv.org·2h
📊Learned Metrics
Flag this post
Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video
arxiv.org·1d
🎧Vorbis Encoding
Flag this post
OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models
arxiv.org·2h
🧠Machine Learning
Flag this post
Loading...Loading more...