@audio/denoise-wiener

import wiener from '@audio/denoise-wiener'

MMSE log-spectral amplitude (Ephraim & Malah 1985) or Wiener (Scalart & Filho 1996) gain on the decision-directed a priori SNR ξ = α·Â²(l−1)/λ(l−1) + (1−α)·max(γ−1, 0) (Ephraim & Malah 1984, eq. 51). α = 0.98 is theirs for an 8 ms frame step (§VI: 256 samples at 8 kHz, a new frame every 64) and is rescaled to the actual step as α^{Δt/8 ms}, so the a priori SNR's memory holds in seconds; applied per frame until 0.3, it ran 1.8× longer at 48 kHz (10.7 ms steps) than at 44.1 kHz (5.8 ms). The floor ξ_min stays −15 dB: −25 dB, Cohen's and Loizou's, left more musical noise on steady white and pink noise (log kurtosis ratio 0.98 and 1.49, against 0.53 and 1.01) and cost PESQ and SIG on the training speech (scripts/speech.mjs). The noise PSD λ is tracked by minimum statistics (Martin 2001) over a 1.5 s window, in batch and stream alike, unless a profile or a noise-only stretch is given; a held note, a sustained vowel or a chord is kept out of it (@audio/noise-estimate's partials, as omlsa has it: clean music cut by more than 3 dB 14.5 → 3.4 %, sung long tones 36.3 → 0.0 %, Slakh mixes 26.6 → 3.3 %; estimator: { partials: false } turns it off). processor(opts) is the gain as an @audio/stft frame process, for a host running its own frames.

wiener(data, { fs })                                           // LSA gain, noise tracked
wiener(data, { fs, rule: 'wiener' })                           // Wiener gain
wiener(data, { fs, noiseFrames: 6 })                           // noise from the first 6 frames

Use when: transparent broadband denoise; the "safe default" for stationary noise.

Part of @audio/denoise — the denoise family umbrella. This README is generated from the umbrella docs.

MIT © audiojs