Clean speech reference
The exact synthetic dialogue before either noise mixture was added.
Download Clean speech referenceThe same short passage was mixed with a steady low hum and with intermittent clicks. Hear the original and two actual FFmpeg outputs on each case, then compare them with the clean source. The intermittent-click case also includes one text-prompted speech estimate and what remains after separation. Compare both with the clean reference before judging the result.
The exact synthetic dialogue before either noise mixture was added.
Download Clean speech reference60 Hz and 120 Hz tones plus seeded noise under the dialogue.
Download Steady hum · originalProduced with FFmpeg highpass=f=100.
Download Steady hum · 100 Hz high-passProduced with FFmpeg afftdn using a fixed noise-floor setting.
Download Steady hum · FFT denoiseGenerated clicks before and during spoken lines.
Download Intermittent clicks · originalThe same high-pass settings applied to the click mixture.
Download Intermittent clicks · 100 Hz high-passThe same FFT denoise settings applied to the click mixture.
Download Intermittent clicks · FFT denoiseThe first WAV returned from the pinned SAM Audio Large model for the prompt “The speaking voice.”
Download Intermittent clicks · SAM Audio speech estimateThe second WAV returned by the same request. Listen for words or syllables that carried over.
Download Intermittent clicks · SAM Audio remainder| Sample | Method | Pause RMS (dBFS) | Difference from clean speech (dBFS RMS) |
|---|---|---|---|
| Steady hum | Original | -23.90 | -23.91 |
| Steady hum | 100 Hz high-pass | -30.60 | -30.29 |
| Steady hum | FFT denoise | -24.06 | -23.22 |
| Intermittent clicks | Original | -37.98 | -39.85 |
| Intermittent clicks | 100 Hz high-pass | -38.00 | -37.64 |
| Intermittent clicks | FFT denoise | -38.92 | -30.35 |
| Intermittent clicks | SAM Audio speech estimate | -74.94 | -40.16 |
The pause measure is the recorded RMS level from 0.15 to 0.80 seconds. The click case deliberately includes a click in that window. The speech-window measure is the RMS of the sample-by-sample difference from the clean reference at the supplied times.
A larger difference can reflect noise, timing, phase, or changes to speech. Use your own listening pass to judge intelligibility. The clean reference comes straight from the synthetic speech generator before noise was added.
The lines are “The blue marker is on the desk,” “Please check the window before you leave,” and “Save the last clean take.” Speech was generated from these original lines with eSpeak NG. No third-party recording was used.
We sent the eight-second intermittent-click mix to the pinned geopti/sam-audio-large model through Replicate with the prompt “The speaking voice.” The request asked for the residual and used no time anchors. The returned WAVs are provided as received. The JSON records the full model revision, prompt, settings, and file hashes.
Only the speech estimate is included in the measurement table. All files were compared from their first sample at their original gain. Listen around 1.53, 3.99, 4.24, and 6.36 seconds for residual clicks and clipped consonants. Listen to the remainder for missing bits of speech.
This is one run on generated speech with a particular mixture and prompt. Evaluate a representative passage of your own recording at matched playback levels before making an editing decision.
To reproduce the second case, replace steady-hum in the names with interrupting-clicks. Use the clean reference and measured windows in the JSON report.
On a real recording, use small reversible changes. If you cannot verify an important word against the original or an alternate track, consider a retake when one is available.
ffmpeg -i steady-hum-original.wav -af 'highpass=f=100' -c:a pcm_s16le steady-hum-high-pass.wav
ffmpeg -i steady-hum-original.wav -af 'afftdn=nr=12:nf=-42:tn=0' -c:a pcm_s16le steady-hum-fft-denoise.wav