🎵 Audio ML

Speech Recognition, Music Information Retrieval, Acoustic Modeling, Sound Classification

Microsoft Says Voice Will Emerge as Primary Input for Next Windows
tech.slashdot.org·1d
🪟Awesome windows command-line
Wrong Again
pearsa.substack.com·1d·
Discuss: Substack
⚡Proof Automation
Antarctic leopard seal 'songs' are surprisingly similar to nursery rhymes
phys.org·2d
🎵Music Universality
Mishearings: Hacking a tiny ASR model to write Dadaist poetry
evanking.io·5d·
Discuss: Hacker News
🎙️Whisper
Agoran: An Agentic Open Marketplace for 6G RAN Automation
arxiv.org·2d
🌊Streaming Systems
Goal Discovery with Causal Capacity for Efficient Reinforcement Learning
arxiv.org·2d
🔲Cellular Automata
A Robust Optimization Approach for Demand Response Participation of Fixed-Frequency Air Conditioners
arxiv.org·1d
🌊Streaming Systems
Generating Feasible and Diverse Synthetic Populations Using Diffusion Models
arxiv.org·2d
🔲Cellular Automata
Forecasting Commodity Price Shocks Using Temporal and Semantic Fusion of Prices Signals and Agentic Generative AI Extracted Economic News
arxiv.org·4d
📈Time Series
Alif Ensemble E4, E6, and E8 Cortex-M85/A32 MCUs and MPUs feature Ethos-U85 NPU for small language models (SLM)
cnx-software.com·2d
🦾ARM Cortex-M
Peer Effect Estimation in the Presence of Simultaneous Feedback and Unobserved Confounders
arxiv.org·2d
🔍Information Retrieval
Sample-efficient LLM Optimization with Reset Replay
arxiv.org·5d
💻Local LLMs
LLM Serving Optimization with Variable Prefill and Decode Lengths
arxiv.org·5d
🌊Streaming Compression
TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptation
arxiv.org·5d
📊Learned Metrics
BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models
arxiv.org·4d
📊Learned Metrics
Enhancing Rumor Detection Methods with Propagation Structure Infused Language Model
arxiv.org·4d
🔍Information Retrieval
Narrative Memory in Machines: Multi-Agent Arc Extraction in Serialized TV
arxiv.org·4d
⧗Information Bottleneck
Towards Safer AI Moderation: Evaluating LLM Moderators Through a Unified Benchmark Dataset and Advocating a Human-First Approach
arxiv.org·4d
🤖AI Curation
SOI is the Root of All Evil: Quantifying and Breaking Similar Object Interference in Single Object Tracking
arxiv.org·2d
👁️Perceptual Hashing
KFFocus: Highlighting Keyframes for Enhanced Video Understanding
arxiv.org·3d
📊Rate-Distortion Theory