Wooseok Kim

Configurable-Bandwidth Time-Frequency Modeling for Efficient Full-Band Speech Enhancement Across Sampling Rates

Speech enhancement systems are often developed for a fixed sampling rate, while time-frequency models become more expensive as the number of frequency bins increases. We propose TF-Refiner, a sampling-frequency-independent model that decouples the deep analysis bandwidth from the full-band input and output. A deep enco...