Merge branch 'avid' into 'main'

Add support for AVID dataset

See merge request fast/speechdatasets.jl!16

README.md

@@ -24,6 +24,9 @@ julia> dataset = TIMIT("/path/to/timit/dir", "outputdir", :train) # :dev | :test
 julia> dataset = INADIACHRONY("/path/to/ina_wav/dir", "outputdir", "/path/to/ina_csv/dir") # ina_csv dir optional
 ...
 
+julia> dataset = AVID("/path/to/avid/dir", "outputdir")
+...
+
 
 julia> for ((signal, fs), supervision) in dataset
            # do something

src/SpeechDatasets.jl

@@ -27,6 +27,7 @@ export
     MINILIBRISPEECH,
     TIMIT,
     INADIACHRONY,
+    AVID,
 
     # Lexicon
     CMUDICT,
@@ -46,6 +47,7 @@ include("corpora/multilingual_librispeech.jl")
 include("corpora/mini_librispeech.jl")
 include("corpora/timit.jl")
 include("corpora/ina_diachrony.jl")
+include("corpora/avid.jl")
 
 include("lexicons.jl")
 

src/corpora/avid.jl

+# SPDX-License-Identifier: CECILL-2.1
+
+function avid_recordings(dir::AbstractString)
+    checkdir(dir)
+
+    recordings = Dict()
+    for (root, subdirs, files) in walkdir(dir)
+        for file in files
+            filename, ext = splitext(file)
+            ext != ".wav" && continue
+            
+            id = filename
+            path = joinpath(root, file)
+
+            audio_src = FileAudioSource(path)
+
+            recordings[id] = Recording(
+                id,
+                audio_src;
+                channels = [1],
+                samplerate = 16000
+            )
+        end
+    end
+    recordings
+end
+
+
+function load_metadata_files(dir::AbstractString)
+    tasksdict = Dict('s' => "SENT", 'p' => "PARA")
+    metadatadict = Dict(key => 
+        readlines(joinpath(dir, "Metadata_with_labels_$(tasksdict[key]).csv")) 
+        for key in keys(tasksdict))
+    return metadatadict
+end
+
+
+function get_metadata(filename, metadatadict)
+    task = split(filename, "_")[3][1]
+    headers = metadatadict[task][1]
+    headers = split(headers, ",")
+    file_metadata = filter(x -> contains(x, filename), metadatadict[task])[1]
+    file_metadata = split(file_metadata, ",")
+    metadata = Dict(
+        headers[i] => file_metadata[i]
+        for i = 1:length(headers)
+    )
+    return metadata
+end
+
+
+function avid_annotations(dir)
+    checkdir(dir)
+
+    annotations = Dict()
+    metadatadict = load_metadata_files(dir)
+
+    for (root, subdirs, files) in walkdir(dir)
+        for file in files
+            filename, ext = splitext(file)
+            ext != ".wav" && continue
+            
+            # extract metadata from csv files
+            metadata = get_metadata(filename, metadatadict)
+            
+            id = filename
+            # generate annotation
+            annotations[id] = Annotation(
+                id, # audio id
+                id, # annotation id
+                -1,  # start and duration is -1 means that we take the whole
+                -1,  # recording
+                [1], # only 1 channel (mono recording)
+                metadata # additional informations   
+            )
+        end
+    end
+    annotations
+end
+
+
+function download_avid(dir)
+    @info "Directory $dir not found.\nDownloading AVID dataset (9.9 GB)"
+    url = "https://zenodo.org/records/10524873/files/AVID.zip?download=1"
+    filename = "AVID.zip"
+    filepath = joinpath(dir,filename)
+    run(`mkdir -p $dir`)
+    run(`wget $url -O $filepath`)
+    @info "Download complete, extracting files"
+    run(`unzip $filepath -d $dir`)
+    run(`rm $filepath`)
+    return joinpath(datadir, "/AVID")
+end
+
+
+function avid_prepare(datadir, outputdir)
+    # Validate the data directory
+    isdir(datadir) || (datadir = download_avid(datadir))
+
+    # Create the output directory.
+    outputdir = mkpath(outputdir)
+    rm(joinpath(outputdir, "recordings.jsonl"), force=true)
+
+    # Recordings
+    recordings = Array{Dict}(undef, 2)
+    recordings_path = joinpath(datadir, "Repository 2")
+    @info "Extracting recordings from $recordings_path"
+    recordings[1] = avid_recordings(recordings_path)
+    # Calibration tones
+    calibtones_path = joinpath(datadir, "Calibration_tones")
+    @info "Extracting recordings from $calibtones_path"
+    recordings[2] = avid_recordings(calibtones_path)
+
+    for (i, manifestpath) in enumerate([joinpath(outputdir, "recordings.jsonl"), joinpath(outputdir, "calibration_tones.jsonl")])
+        open(manifestpath, "w") do f
+            writemanifest(f, recordings[i])
+        end
+    end
+
+    # Annotations
+    annotations_path = recordings_path
+    @info "Extracting annotations from $annotations_path"
+    annotations = avid_annotations(annotations_path)
+        
+    manifestpath = joinpath(outputdir, "annotations.jsonl")
+    @info "Creating $manifestpath"
+    open(manifestpath, "w") do f
+        writemanifest(f, annotations)
+    end
+end
+
+
+function AVID(datadir, outputdir)
+    if ! (isfile(joinpath(outputdir, "recordings.jsonl")) &&
+          isfile(joinpath(outputdir, "calibration_tones.jsonl")) &&
+          isfile(joinpath(outputdir, "annotations.jsonl")))
+        avid_prepare(datadir, outputdir)
+    end
+    dataset(outputdir, "")
+end

src/corpora/ina_diachrony.jl

 # SPDX-License-Identifier: CECILL-2.1
 
-function checkdir(dir::AbstractString)
-    isdir(dir) || throw(ArgumentError("$dir is not an existing directory"))
-end
-
 function ina_diachrony_recordings(dir::AbstractString)
     checkdir(dir)
 

src/manifest_io.jl

@@ -136,3 +136,6 @@ Load Recording/Annotation manifest from `path`.
 """
 load(T::Type{<:Union{Recording, Annotation}}, path) = open(f -> readmanifest(f, T), path, "r")
 
+function checkdir(dir::AbstractString)
+    isdir(dir) || throw(ArgumentError("$dir is not an existing directory"))
+end