# Forensic Speech Enhancer

Speech-focused cleanup for noisy evidence and interview recordings: documented FFmpeg filter chains with presets for evidence clarity, broadcast, telephone band and transcription prep.

> Canonical page: https://elysiatools.com/en/tools/audio-forensic-enhancer

- **Category:** Media

- **Keywords:** forensic audio, speech enhancement, evidence audio, interview cleanup, afftdn, speechnorm, deesser, noise gate, telephone band, intelligibility, transcription prep, asr prep, ffmpeg chain, swgde

## Overview

A transparent work-product generator for speech audio that has to be understood, not beautified: noisy evidence recordings, police/procedural interviews, field footage audio. Following the SWGDE technical notes on FFmpeg for forensic audio examination, the tool never touches your original - it renders an enhanced derivative through a documented, reproducible FFmpeg filter chain that is recorded verbatim in the result metadata, so the processing history of the work product can be reported alongside the exhibit. Four chain presets: EVIDENCE CLARITY (the conservative default) keeps the full speech band and applies FFT denoising (afftdn with a chosen reduction and noise floor), de-essing, gentle 2:1 leveling and speech normalization with a true-peak-safe limiter; INTERVIEW BROADCAST adds a 100 Hz-8 kHz wideband speech window with lighter denoising for publishable interview audio; TELEPHONE BAND band-limits to the classic 300-3400 Hz telephony passband - the range classic intelligibility research standardized - plus a noise gate for pauses; TRANSCRIPTION PREP runs the strongest denoise and gating to feed automatic speech recognition, where consistent level matters more than naturalness. Strength (light / standard / strong) scales the denoise amount and noise-floor setting together, so the chain stays balanced. The report measures the input and output with a BS.1770-4 meter (integrated loudness, true peak) and estimates the noise floor before and after from the quietest 10 percent of 100 ms blocks, so the denoise effect is a number, not a claim. Every enhancement is a processing artifact on a copy: keep the original, document the chain, and disclose the enhancement in your work product - this tool makes the disclosure copy-pasteable.

## Inputs

- **Evidence / interview audio** (file)
- **Enhancement preset** (select)
- **Strength** (select)
- **Output format** (select)

## When to use

- Preparing noisy recorded interviews or legal audio exhibits where speech intelligibility must be maximized without altering the source file.
- Conditioning low-level or background-heavy speech recordings before submitting them to automatic speech recognition (ASR) engines.
- Documenting chain-of-custody processing history for forensic case reports, disclosures, or broadcast publication copies.

## How it works

- Select an audio file and choose an enhancement preset: Evidence clarity, Interview broadcast, Telephone band, or Transcription prep.
- Adjust the processing strength to light, standard, or strong, which balances FFT denoising depth and noise floor tracking proportionately.
- Pick your export container (24-bit PCM WAV, lossless FLAC, or 320 kbps MP3) and render the enhanced copy.
- Review the measured output report detailing integrated loudness, true-peak levels, noise floor reduction in decibels, and the reproducible FFmpeg filter chain.

## Use cases

- Forensic audio examiners generating defensible, documented derivatives of noisy witness recordings for courtroom presentation.
- Transcriptionists and researchers isolating dialogue from high-noise field interviews to boost automatic transcription accuracy.
- Investigative journalists cleaning up noisy archival wiretaps or field recordings using standard speech frequency cutoffs.

## Frequently asked questions

### Does this tool alter or overwrite my original audio file?

No. The original file is never modified; enhancements are rendered strictly to a separate derivative copy.

### How is the filter chain documented for legal disclosures?

The verbatim FFmpeg filter chain string, parameters, and before-and-after loudness metrics are included directly in the processing metadata report.

### What is the difference between Evidence clarity and Transcription prep?

Evidence clarity preserves the full audible speech band with conservative denoising and leveling, while Transcription prep applies aggressive gating and denoising tuned for automated speech-to-text engines.

### What audio export formats are supported?

You can export the enhanced derivative as 24-bit PCM WAV, lossless FLAC, or 320 kbps MP3.

### How is the noise floor reduction calculated?

The analyzer measures input and output levels across the quietest 10 percent of 100 ms blocks using BS.1770-4 integrated loudness and true-peak metering.

## Related tools

- [Assistive Listening Enhancer](https://elysiatools.com/en/tools/audio-assistive-listening-enhancer): Clarify listening audio with low-frequency cleanup, speech-presence EQ, conservative denoising, and level protection.
- [Classroom Recording Cleaner](https://elysiatools.com/en/tools/audio-classroom-recording-cleaner): Clean lecture recordings with speech-focused EQ, hum reduction, peak control, and optional long-silence trimming.
- [Audio Remote Guest Rescue](https://elysiatools.com/en/tools/audio-remote-guest-rescue): Reduce room echo, broadband noise, boxiness, and dullness in remote guest recordings.
- [FFmpeg Audio Noise Reduction](https://elysiatools.com/en/tools/ffmpeg-audio-noise-reduction): Professional audio noise reduction using FFmpeg advanced filters (highpass, afftdn, loudnorm) for optimal audio cleaning
- [Audio Plosive Reducer](https://elysiatools.com/en/tools/audio-plosive-reducer): Reduce P/B plosive thumps in close-mic speech while preserving voice body.
- [Audio Sibilance Map](https://elysiatools.com/en/tools/audio-sibilance-map): Map harsh S, T, and SH regions so de-essing can target the right moments instead of dulling the whole voice.
- [Audio DC Offset Fixer](https://elysiatools.com/en/tools/audio-dc-offset-fixer): Detect and remove DC offset from audio
- [Audio Metadata Remover](https://elysiatools.com/en/tools/audio-metadata-remover): Strip technical metadata from an audio file for privacy before sharing

## Samples

- [Speech Learning & Safety Audio Samples](https://elysiatools.com/en/samples/audio-learning-safety-samples): Deterministic synthetic WAV inputs for pronunciation comparison, dictation preflight, alert degradation, and voice privacy tools.
- [Copyright-Free FLAC Audio Samples](https://elysiatools.com/en/samples/flac-samples): Lossless FLAC audio samples for testing and development, mirrored from MP3 set with nature sounds and meditation music
- [Copyright-Free MP3 Audio Samples](https://elysiatools.com/en/samples/mp3-samples): Collection of royalty-free audio samples for testing and development purposes including nature sounds, meditation music, and ambient audio
- [Copyright-Free WAV Audio Samples](https://elysiatools.com/en/samples/wav-samples): Uncompressed PCM WAV audio samples for testing and development, mirrored from MP3 set with nature sounds and meditation music