11 papers
MPASCNet: Magnitude-Phase-Aware Adaptive Spectral Compression for Compressed Music Restoration
Xinlong Deng, Yu Xia, Qiuqiang Kong +2
Compressed music restoration aims to recover high-fidelity audio from lossy codecs such as MP3 by restoring missing spectral content and reducing coding artifacts. Recently, genera…
Voices of Civilizations: A Multilingual QA Benchmark for Global Music Understanding
Shangda Wu, Ziya Zhou, Yongyi Zang +4
We introduce Voices of Civilizations, the first multilingual QA benchmark for evaluating audio LLMs' cultural comprehension on full-length music recordings. Covering 380 tracks acr…
Summary of The Inaugural Music Source Restoration Challenge
Yongyi Zang, Jiarui Hai, Wanying Ge +5
Music Source Restoration (MSR) aims to recover original, unprocessed instrument stems from professionally mixed and degraded audio, requiring the reversal of both production effect…
MSRBench: A Benchmarking Dataset for Music Source Restoration
Yongyi Zang, Jiarui Hai, Wanying Ge +5
Music Source Restoration (MSR) extends source separation to realistic settings where signals undergo production effects (equalization, compression, reverb) and real-world degradati…
Music Source Restoration
Yongyi Zang, Zheqi Dai, Mark D. Plumbley +1
We introduce Music Source Restoration (MSR), a novel task addressing the gap between idealized source separation and real-world music production. Current Music Source Separation (M…
Training-Free Multi-Step Audio Source Separation
Yongyi Zang, Jingyi Li, Qiuqiang Kong
Audio source separation aims to separate a mixture into target sources. Previous audio source separation systems usually conduct one-step inference, which does not fully explore th…
GSound-SIR: A Spatial Impulse Response Ray-Tracing and High-order Ambisonic Auralization Python Toolkit
Yongyi Zang, Qiuqiang Kong
Accurate and efficient simulation of room impulse responses is crucial for spatial audio applications. However, existing acoustic ray-tracing tools often operate as black boxes and…
Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders
Dichucheng Li, Yongyi Zang, Qiuqiang Kong
Automatic Music Transcription (AMT), aiming to get musical notes from raw audio, typically uses frame-level systems with piano-roll outputs or language model (LM)-based systems wit…
DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning
Xiquan Li, Wenxi Chen, Ziyang Ma +5
While automated audio captioning (AAC) has made notable progress, traditional fully supervised AAC models still face two critical challenges: the need for expensive audio-text pair…
Language-Queried Target Sound Extraction Without Parallel Training Data
Hao Ma, Zhiyuan Peng, Xu Li +4
Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extens…
Towards Out-of-Distribution Detection in Vocoder Recognition via Latent Feature Reconstruction
Renmingyue Du, Jixun Yao, Qiuqiang Kong +1
Advancements in synthesized speech have created a growing threat of impersonation, making it crucial to develop deepfake algorithm recognition. One significant aspect is out-of-dis…