REVIEW 3 cited by
Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration
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
This paper proposes a generative pretraining foundation model for high-quality speech restoration tasks. By directly operating on complex-valued short-time Fourier transform coefficients, our model does not rely on any vocoders for time-domain signal reconstruction. As a result, our model simplifies the synthesis process and removes the quality upper-bound introduced by any mel-spectrogram vocoder compared to prior work SpeechFlow. The proposed method is evaluated on multiple speech restoration tasks, including speech denoising, bandwidth extension, codec artifact removal, and target speaker extraction. In all scenarios, finetuning our pretrained model results in superior performance over strong baselines. Notably, in the target speaker extraction task, our model outperforms existing systems, including those leveraging SSL-pretrained encoders like WavLM. The code and the pretrained checkpoints are publicly available in the NVIDIA NeMo framework.
Forward citations
Cited by 3 Pith papers
-
A2SB: Audio-to-Audio Schrodinger Bridges
A2SB applies Schrödinger bridges to music restoration, achieving state-of-the-art bandwidth extension and inpainting at 44.1kHz in a single vocoder-free model.
-
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.
-
SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
A cascaded pipeline of audio compression, latent diffusion extraction, and generative correction achieves state-of-the-art target speech extraction quality and intelligibility on Libri2Mix and out-of-domain data.
Discussion (0). Continue with ORCID to comment.