Detect true mp3 bitrate

detect-mp3-bitrate.sh

#!/usr/bin/env bash

set -euo pipefail

function main() {
    # Check for argument
    if [ $# -ne 1 ]
    then
        echo "usage: $0 INFILE"
        exit 1
    fi

    # Define bitrates to check
    local INFILE="$1"
    local BITRATES="320 256 224 192 160 128 112 96 80 64 56 48 40 32"

    # Check if file exists
    if ! [ -f "$INFILE" ]
    then
        echo "file not found: $INFILE"
        exit 1
    fi

    # Remove temporary files on exit
    trap 'rm -f .tmp*.wav .tmp*.mp3' EXIT

    # Check if lame and sox commands exist
    for cmd in lame sox
    do
        if ! which "$cmd" >/dev/null
        then
            echo "command not found: $cmd"
            exit 1
        fi
    done

    # Decode original file to wav and invert amplitude
    decode "$INFILE" .tmp.src.wav -1

    # Decode file to bitrate and compare differences
    for BITRATE in $BITRATES
    do
        # compress "$INFILE" .tmp.mp3 "$bitrate"
        compress "$INFILE" .tmp.mp3 "$BITRATE"
        decode .tmp.mp3 .tmp.wav

        printf "%3s: %s\n" "$BITRATE" \
            "$(compare .tmp.src.wav .tmp.wav \
                2>&1 \
                | grep 'RMS.*amplitude' \
                | awk '{print $3}')"
    done
}

# Compress mp3 file with given constant bit rate
function compress() {
    local INFILE="$1"
    local OUTFILE="$2"
    local BITRATE="$3"

    lame \
        --quiet \
        -q 0 \
        "$INFILE" \
        -b "$BITRATE" \
        "$OUTFILE"
}

# Decode mp3 file into wav
function decode() {
    local INFILE="$1"
    local OUTFILE="$2"
    local VOLUME="${3-1}" # set to -1 to invert signal

    lame \
        --quiet \
        -q 0 \
        "$INFILE" \
        --decode \
        .tmp.decode.wav

    # resample to avoid compare issues
    sox \
        --volume "${VOLUME}" \
        .tmp.decode.wav \
        --rate 44100 \
        "$OUTFILE" >/dev/null 2>&1
}

# Compare two wav files, assume one is inverted
function compare() {
    local FILE1="$1"
    local FILE2="$2"

    sox \
        --combine mix \
        "$FILE1" "$FILE2" \
        --null \
        stat
}

main "$@"

I plotted the spectrogram of the 320k and the "320k->downsampled to 56k -> upsampled to 320k" files, took a screenshot and subtracted the images from each other. I'm looking for discernable patterns. The "blocks" are misleading, that's just me croaking scales. The faint, pink, belt in the middle is low-frequency noise (<100 Hz) on the left channel - that seems to be more present in the 320k file than in the upsampled one.