A 0.45M-parameter causal UNet-style denoiser with look-back frames and GRUs reports 22.34 dB SI-SDR on full-band VCTK data and RTF 0.014 on a Pixel 7.
Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech Separation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Lightweight DNN for Full-Band Speech Denoising on Mobile Devices: Exploiting Long and Short Temporal Patterns
A 0.45M-parameter causal UNet-style denoiser with look-back frames and GRUs reports 22.34 dB SI-SDR on full-band VCTK data and RTF 0.014 on a Pixel 7.