Cover Image

Efficient Vocal Source Separation Through Windowed Sink Attention

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Benetatos, Christodoulos, Zang, Yongyi, Leistikow, Randal
Format:	Preprint
Published:	2025
Subjects:	Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FlowSynth: Instrument Generation Through Distributional Flow Matching and Test-Time Search
by: Yang, Qihui, et al.
Published: (2025)

Learning Interpretable Features in Audio Latent Spaces via Sparse Autoencoders
by: Paek, Nathan, et al.
Published: (2025)

Smule Renaissance Small: Efficient General-Purpose Vocal Restoration
by: Zang, Yongyi, et al.
Published: (2025)

PromptReverb: Multimodal Room Impulse Response Generation Through Latent Rectified Flow Matching
by: Vosoughi, Ali, et al.
Published: (2025)

StylePitcher: Generating Style-Following and Expressive Pitch Curves for Versatile Singing Tasks
by: Huang, Jingyue, et al.
Published: (2025)

Training-Free Multi-Step Audio Source Separation
by: Zang, Yongyi, et al.
Published: (2025)

GSound-SIR: A Spatial Impulse Response Ray-Tracing and High-order Ambisonic Auralization Python Toolkit
by: Zang, Yongyi, et al.
Published: (2025)

Mel-RoFormer for Vocal Separation and Vocal Melody Transcription
by: Wang, Ju-Chiang, et al.
Published: (2024)

The Interpretation Gap in Text-to-Music Generation Models
by: Zang, Yongyi, et al.
Published: (2024)

Music Source Restoration
by: Zang, Yongyi, et al.
Published: (2025)

MSRBench: A Benchmarking Dataset for Music Source Restoration
by: Zang, Yongyi, et al.
Published: (2025)

Ambisonizer: Neural Upmixing as Spherical Harmonics Generation
by: Zang, Yongyi, et al.
Published: (2024)

Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions
by: Kim, Euiyeon, et al.
Published: (2025)

SAMUeL: Efficient Vocal-Conditioned Music Generation via Soft Alignment Attention and Latent Diffusion
by: Cheung, Hei Shing, et al.
Published: (2025)

Are you really listening? Boosting Perceptual Awareness in Music-QA Benchmarks
by: Zang, Yongyi, et al.
Published: (2025)

Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders
by: Li, Dichucheng, et al.
Published: (2025)

Generating Separated Singing Vocals Using a Diffusion Model Conditioned on Music Mixtures
by: Plaja-Roglans, Genís, et al.
Published: (2025)

Efficient Area-based and Speaker-Agnostic Source Separation
by: Strauss, Martin, et al.
Published: (2024)

Summary of The Inaugural Music Source Restoration Challenge
by: Zang, Yongyi, et al.
Published: (2026)

SingFake: Singing Voice Deepfake Detection
by: Zang, Yongyi, et al.
Published: (2023)

DJCM: A Deep Joint Cascade Model for Singing Voice Separation and Vocal Pitch Estimation
by: Wei, Haojie, et al.
Published: (2024)

FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer
by: Wang, Haoxu, et al.
Published: (2025)

Source Separation for A Cappella Music
by: Lanzendörfer, Luca A., et al.
Published: (2025)

A Reliable and Efficient Detection Pipeline for Rodent Ultrasonic Vocalizations
by: Anis, Sabah Shahnoor, et al.
Published: (2025)

Music Information Retrieval on Representative Mexican Folk Vocal Melodies Through MIDI Feature Extraction
by: Reyes, Mario Alberto Vallejo
Published: (2025)

Source Separation by Flow Matching
by: Scheibler, Robin, et al.
Published: (2025)

SynthTab: Leveraging Synthesized Data for Guitar Tablature Transcription
by: Zang, Yongyi, et al.
Published: (2023)

Dissecting Performance Degradation in Audio Source Separation under Sampling Frequency Mismatch
by: Imamura, Kanami, et al.
Published: (2026)

Determined Multichannel Blind Source Separation with Clustered Source Model
by: Wang, Jianyu, et al.
Published: (2024)

UniVocal: Unified Speech-Singing Code-Switching Synthesis
by: Shi, Yufei, et al.
Published: (2026)

NVBench: A Benchmark for Speech Synthesis with Non-Verbal Vocalizations
by: Xue, Liumeng, et al.
Published: (2026)

Task-Aware Unified Source Separation
by: Saijo, Kohei, et al.
Published: (2024)

SVDD 2024: The Inaugural Singing Voice Deepfake Detection Challenge
by: Zhang, You, et al.
Published: (2024)

Towards Practical Real-Time Low-Latency Music Source Separation
by: Wu, Junyu, et al.
Published: (2025)

Voices of Civilizations: A Multilingual QA Benchmark for Global Music Understanding
by: Wu, Shangda, et al.
Published: (2026)

Affectron: Emotional Speech Synthesis with Affective and Contextually Aligned Nonverbal Vocalizations
by: Cho, Deok-Hyeon, et al.
Published: (2026)

LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment Generation
by: Wang, Qi, et al.
Published: (2026)

Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs
by: Anand, et al.
Published: (2025)

Modeling and Estimation of Vocal Tract and Glottal Source Parameters Using ARMAX-LF Model
by: Lia, Kai, et al.
Published: (2024)

A Dataset for Automatic Vocal Mode Classification
by: Hinrichs, Reemt, et al.
Published: (2026)