timit.jl

# SPDX-License-Identifier: CECILL-2.1

#######################################################################


const TIMIT_SUBSETS = Dict(
    "train" => "train",
    "dev" => "dev",
    "test" => "test"
)


const TIMIT_DEV_SPK_LIST = Set([
"faks0",
    "fdac1",
    "fjem0",
    "mgwt0",
    "mjar0",
    "mmdb1",
    "mmdm2",
    "mpdf0",
    "fcmh0",
    "fkms0",
    "mbdg0",
    "mbwm0",
    "mcsh0",
    "fadg0",
    "fdms0",
    "fedw0",
    "mgjf0",
    "mglb0",
    "mrtk0",
    "mtaa0",
    "mtdt0",
    "mthc0",
    "mwjg0",
    "fnmr0",
    "frew0",
    "fsem0",
    "mbns0",
    "mmjr0",
    "mdls0",
    "mdlf0",
    "mdvc0",
    "mers0",
    "fmah0",
    "fdrw0",
    "mrcs0",
    "mrjm4",
    "fcal1",
    "mmwh0",
    "fjsj0",
    "majc0",
    "mjsw0",
    "mreb0",
    "fgjd0",
    "fjmg0",
    "mroa0",
    "mteb0",
    "mjfc0",
    "mrjr0",
    "fmml0",
    "mrws1"
])


const TIMIT_TEST_SPK_LIST = Set([
    "mdab0",
    "mwbt0",
    "felc0",
    "mtas1",
    "mwew0",
    "fpas0",
    "mjmp0",
    "mlnt0",
    "fpkt0",
    "mlll0",
    "mtls0",
    "fjlm0",
    "mbpm0",
    "mklt0",
    "fnlp0",
    "mcmj0",
    "mjdh0",
    "fmgd0",
    "mgrt0",
    "mnjm0",
    "fdhc0",
    "mjln0",
    "mpam0",
    "fmld0"
])


TIMIT_PHONE_MAP48 = Dict(
    "aa"    => "aa",
    "ae"    => "ae",
    "ah"    => "ah",
    "ao"    => "ao",
    "aw"    => "aw",
    "ax"    => "ax",
    "ax-h"  => "ax",
    "axr"   => "er",
    "ay"    => "ay",
    "b"     => "b",
    "bcl"   => "vcl",
    "ch"    => "ch",
    "d"     => "d",
    "dcl"   => "vcl",
    "dh"    => "dh",
    "dx"    => "dx",
    "eh"    => "eh",
    "el"    => "el",
    "em"    => "m",
    "en"    => "en",
    "eng"   => "ng",
    "epi"   => "epi",
    "er"    => "er",
    "ey"    => "ey",
    "f"     => "f",
    "g"     => "g",
    "gcl"   => "vcl",
    "h#"    => "sil",
    "hh"    => "hh",
    "hv"    => "hh",
    "ih"    => "ih",
    "ix"    => "ix",
    "iy"    => "iy",
    "jh"    => "jh",
    "k"     => "k",
    "kcl"   => "cl",
    "l"     => "l",
    "m"     => "m",
    "n"     => "n",
    "ng"    => "ng",
    "nx"    => "n",
    "ow"    => "ow",
    "oy"    => "oy",
    "p"     => "p",
    "pau"   => "sil",
    "pcl"   => "cl",
    "q"     => "",
    "r"     => "r",
    "s"     => "s",
    "sh"    => "sh",
    "t"     => "t",
    "tcl"   => "cl",
    "th"    => "th",
    "uh"    => "uh",
    "uw"    => "uw",
    "ux"    => "uw",
    "v"     => "v",
    "w"     => "w",
    "y"     => "y",
    "z"     => "z",
    "zh"    => "zh"
)


TIMIT_PHONE_MAP39 = Dict(
    "aa"    => "aa",
    "ae"    => "ae",
    "ah"    => "ah",
    "ao"    => "aa",
    "aw"    => "aw",
    "ax"    => "ah",
    "ax-h"  => "ah",
    "axr"   => "er",
    "ay"    => "ay",
    "b"     => "b",
    "bcl"   => "sil",
    "ch"    => "ch",
    "d"     => "d",
    "dcl"   => "sil",
    "dh"    => "dh",
    "dx"    => "dx",
    "eh"    => "eh",
    "el"    => "l",
    "em"    => "m",
    "en"    => "n",
    "eng"   => "ng",
    "epi"   => "sil",
    "er"    => "er",
    "ey"    => "ey",
    "f"     => "f",
    "g"     => "g",
    "gcl"   => "sil",
    "h#"    => "sil",
    "hh"    => "hh",
    "hv"    => "hh",
    "ih"    => "ih",
    "ix"    => "ih",
    "iy"    => "iy",
    "jh"    => "jh",
    "k"     => "k",
    "kcl"   => "sil",
    "l"     => "l",
    "m"     => "m",
    "n"     => "n",
    "ng"    => "ng",
    "nx"    => "n",
    "ow"    => "ow",
    "oy"    => "oy",
    "p"     => "p",
    "pau"   => "sil",
    "pcl"   => "sil",
    "q"     => "",
    "r"     => "r",
    "s"     => "s",
    "sh"    => "sh",
    "t"     => "t",
    "tcl"   => "sil",
    "th"    => "th",
    "uh"    => "uh",
    "uw"    => "uw",
    "ux"    => "uw",
    "v"     => "v",
    "w"     => "w",
    "y"     => "y",
    "z"     => "z",
    "zh"    => "sh"
)

#######################################################################


function timit_prepare(timitdir, dir; audio_fmt="SPHERE")
    # Validate the data directory
    ! isdir(timitdir) && throw(ArgumentError("invalid path $(timitdir)"))

    # Create the output directory.
    dir = mkpath(dir)

    for (subset, subdir) in [("train", "train"), ("dev", "train"), ("test", "test")]
        sdir = joinpath(timitdir, subdir)

        # Recordings
        manifestpath = joinpath(dir, "recordings.jsonl")
        @debug "preparing $manifestpath"
        recordings = timit_recordings(sdir; fmt=audio_fmt)
        open(manifestpath, "w") do f
            writemanifest(f, recordings)
        end

        # Supervision
        manifestpath = joinpath(dir, "supervisions-$(subset).jsonl")
        @debug "Preparing $manifestpath"
        supervisions = timit_supervisions(sdir)
        open(manifestpath, "w") do f
            writemanifest(f, supervisions)
        end
    end
end


function timit_recordings(dir::AbstractString; fmt="SPHERE")
    ! isdir(dir) && throw(ArgumentError("expected directory $dir"))

    recordings = Dict()
    for (root, subdirs, files) in walkdir(dir)
        for file in files
            name, ext = splitext(file)
            ext != ".wav" && continue
            spk = basename(root)
            path = joinpath(root, file)
            id = "timit_$(spk)_$(name)"

            audio_src = if fmt == "SPHERE"
                CmdAudioSource(`sph2pipe -f wav $path`)
            else
                FileAudioSource(path)
            end

            recordings[id] = Recording(
                id,
                audio_src;
                channels = [1],
                samplerate = 16000
            )
        end
    end
    recordings
end


function timit_supervisions(dir)
    ! isdir(dir) && throw(ArgumentError("expected directory $dir"))
    splitline(line) = rsplit(line, limit=3)

    supervisions = Dict()
    for (root, subdirs, files) in walkdir(dir)
        for file in files
            name, ext = splitext(file)
            ext != ".wrd" && continue

            _, dialect, spk = rsplit(root, "/", limit=3)
            path = joinpath(root, file)
            id = "timit_$(spk)_$(name)"

            slines = map(splitline, eachline(path))
            starts, ends, words = zip(slines...)
            start_ts = parse(Int, first(starts)) / 16000
            end_ts = parse(Int, last(ends)) / 16000
            dur = end_ts - start_ts

            supervisions[id] = Supervision(
                id, id, start_ts, dur, [1],
                Dict(
                     "text" => join(words, " "),
                     "dialect" => dialect,
                     "speaker" => spk,
                     "sex" => string(first(spk))
                )
            )
        end
    end
    supervisions
end


function TIMIT(timitdir, dir, subset)
    if ! (isfile(joinpath(dir, "recordings.jsonl")) &&
          isfile(joinpath(dir, "supervisions-train.jsonl")) &&
          isfile(joinpath(dir, "supervisions-dev.jsonl")) &&
          isfile(joinpath(dir, "supervisions-test.jsonl")))
        timit_prepare(timitdir, dir)
    end
    dataset(dir, subset)
end