collaborators

11 papers

eess.AS2026

Music Restoration via Latent Operator Optimization and Diffusion Model Priors

Michal Å vento, Eloi Moliner, Valtteri Kallinen +3

Music restoration seeks to recover a clean signal from an observed recording degraded by an unknown effect, distortion, or corruption. Existing systems often rely on paired trainin…

cs.SD2026

Frequency-Aware Self-Supervised Music Representation Learning

Yicheng Gu, Junan Zhang, Jerry Li +2

Self-supervised learning (SSL) has emerged as an essential paradigm for music information retrieval (MIR). While current SSL models achieve state-of-the-art performance across vari…

cs.SD2026

Aliasing-Free Neural Audio Synthesis

Yicheng Gu, Junan Zhang, Chaoren Wang +3

In neural audio synthesis, neural vocoders and codecs are models that reconstruct waveforms from acoustic and latent representations, which are essential to the resulting audio qua…

cs.SD2026

Deep Regularized RNNs for Virtual Analog Modeling

V. Valtteri Kallinen, Lauri Juvela, Thom Sherson

Virtual analog (VA) modeling methods seek to emulate analog audio hardware using digital signal processing (DSP). Modeling approaches fall into three broad categories: white-box me…

cs.SD2026

HiFi-Glot: High-Fidelity Neural Formant Synthesis with Differentiable Resonant Filters

Yicheng Gu, Pablo Pérez Zarazaga, Chaoren Wang +4

Formant synthesis aims to generate speech with controllable formant structures, enabling precise control of vocal resonance and phonetic features. However, while existing formant s…

eess.AS2026

Nord-Parl-TTS: Finnish and Swedish TTS Dataset from Parliament Speech

Zirui Li, Jens Edlund, Yicheng Gu +3

Text-to-speech (TTS) development is limited by scarcity of high-quality, publicly available speech data for most languages outside a few high-resource languages. We present Nord-Pa…