Recent Research Signals

Found 18 results

Filtering papers...

Paper	Possible Impact	Features	Possible Business Area
Scalable Music Cover Retrieval Using Lyrics-Aligned Audio Embeddings Sound	Finds different versions of the same song.	Code	Image Recognition (79%)	Score: 2 4 days ago
DSA-Tokenizer: Disentangled Semantic-Acoustic Tokenization via Flow Matching-based Hierarchical Fusion Sound	Separates talking into meaning and sound.	Huawei Code	Speech Recognition (77%)	Score: 2 6 days ago
WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem Sound	Helps computers understand a rare Chinese language.	Code	Speech Recognition (77%)	Score: 2 4 days ago
Towards Realistic Synthetic Data for Automatic Drum Transcription Sound	Teaches computers to hear drum music perfectly.	Code	Speech Recognition (75%)	Score: 2 6 days ago
RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios Sound	Tests AI's hearing in noisy, real-world sounds.	Code	Simulation (77%)	Score: 1 5 days ago
Diffusion-based Frameworks for Unsupervised Speech Enhancement Sound	Cleans up noisy voice recordings automatically.	Code	Presentations (74%)	Score: 1 5 days ago
Unifying Speech Recognition, Synthesis and Conversion with Autoregressive Transformers Sound	One AI understands and makes all speech sounds.	Code	Speech Recognition (79%)	Score: 1 5 days ago
SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing Sound	Lets AI understand and create speech, music, and sound.	Code	Natural Language Processing (79%)	Score: 1 6 days ago
Linear Complexity Self-Supervised Learning for Music Understanding with Random Quantizer Sound	Makes music AI smaller, faster, and cheaper.	Code	Natural Language Processing (77%)	Score: 1 6 days ago
HeartMuLa: A Family of Open Sourced Music Foundation Models Sound	Creates music from text, lyrics, or sounds.	Code	Music Label (76%)	Score: 1 5 days ago
FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning Sound	Lets computers talk with your own voice.	Code	Speech Recognition (77%)	Score: 1 4 days ago
SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models Sound	Makes computers hear like humans do.	Code	Natural Language Processing (78%)	Score: 1 4 days ago
Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception Sound	Lets AI know when it hears wrong.	NVIDIA	Speech Recognition (82%)	Score: 1 6 days ago
Stable Differentiable Modal Synthesis for Learning Nonlinear Dynamics Sound	Teaches computers to make realistic sounds.		Simulation (75%)	Score: 0 5 days ago
Research on Piano Timbre Transformation System Based on Diffusion Model Sound	Turns any music into piano music.		Musical Instruments (77%)	Score: 0 6 days ago
Analysis of the Maximum Prediction Gain of Short-Term Prediction on Sustained Speech Sound	Makes speech sound clearer with less data.		Speech Recognition (76%)	Score: 0 6 days ago
Population-Aligned Audio Reproduction With LLM-Based Equalizers Sound	Talk to your speakers to change the sound.		Natural Language Processing (78%)	Score: 0 6 days ago
Self-supervised restoration of singing voice degraded by pitch shifting using shallow diffusion Sound	Fixes singing voice pitch changes without sounding weird.		Speech Recognition (76%)	Score: 0 5 days ago