REVIEW 4 cited by
NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Conventionally, audio super-resolution models fixed the initial and the target sampling rates, which necessitate the model to be trained for each pair of sampling rates. We introduce NU-Wave 2, a diffusion model for neural audio upsampling that enables the generation of 48 kHz audio signals from inputs of various sampling rates with a single model. Based on the architecture of NU-Wave, NU-Wave 2 uses short-time Fourier convolution (STFC) to generate harmonics to resolve the main failure modes of NU-Wave, and incorporates bandwidth spectral feature transform (BSFT) to condition the bandwidths of inputs in the frequency domain. We experimentally demonstrate that NU-Wave 2 produces high-resolution audio regardless of the sampling rate of input while requiring fewer parameters than other models. The official code and the audio samples are available at https://mindslab-ai.github.io/nuwave2.
Forward citations
Cited by 4 Pith papers
-
Semantic Sampling via Learnable Observation Front Ends
Learnable acoustic filterbanks plus constrained mixing and temporal readout produce more informative low-rate observations for speech reconstruction than fixed waveform sampling at the same budget.
-
HiFi-SR: A Unified Generative Transformer-Convolutional Adversarial Network for High-Fidelity Speech Super-Resolution
HiFi-SR is a single end-to-end transformer-convolutional GAN that upscales speech from 4 to 32 kHz inputs to 48 kHz with slightly better spectral distance and listener preference than existing two-stage systems.
-
Bridge-SR: Schr\"odinger Bridge for Efficient SR
Bridge-SR applies tractable Schrödinger bridge models to waveform-domain speech super-resolution, and with 1.7M parameters reports the lowest log-spectral distance on VCTK while matching diffusion quality at 4 sampling steps.
-
Inference-time Scaling for Diffusion-based Audio Super-resolution
Generating 120 candidate super-resolved audios and choosing the best by task-specific verifiers improves speech, music, and sound effects over single-sample diffusion output, at 120x compute.
Discussion (0). Continue with ORCID to comment.