version 0.11

CHANGELOG.md

 # Tags
 
+## [0.11.0](https://https://gitlab.lisn.upsaclay.fr/fast/speechcorpora.jl/-/tags/v0.11.0) - 21/05/2024
+### Added
+- filtering speech dataset based on recording id.
+### Improved
+- Faster TIMIT preparation
+
 ## [0.10.0](https://https://gitlab.lisn.upsaclay.fr/fast/speechcorpora.jl/-/tags/v0.10.0) - 22/02/2024
 ### Added
 - extract alignments from TIMIT

Project.toml

 name = "SpeechDatasets"
 uuid = "ae813453-fab8-46d9-ab8f-a64c05464021"
 authors = ["Lucas ONDEL YANG <lucas.ondel@cnrs.fr>"]
-version = "0.10.0"
+version = "0.11.0"
 
 [deps]
 JSON = "682c06a0-de6a-54ab-a142-c8b1cf79cde6"

src/corpora/timit.jl

@@ -232,23 +232,71 @@ function timit_prepare(timitdir, dir; audio_fmt="SPHERE")
     dir = mkpath(dir)
     rm(joinpath(dir, "recordings.jsonl"), force=true)
 
-    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, "a") do f
-            writemanifest(f, recordings)
+    ## Recordings
+    @info "Extracting recordings from $timitdir/train"
+    train_recordings = timit_recordings(joinpath(timitdir, "train"); fmt=audio_fmt)
+
+    # We extract the name of speakers that are not in the dev set
+    TIMIT_TRAIN_SPK_LIST = Set()
+    for id in keys(train_recordings)
+        _, spk, _ = split(id, "_")
+        if spk ∉ TIMIT_DEV_SPK_LIST
+            push!(TIMIT_TRAIN_SPK_LIST, spk)
         end
+    end
+
+    @info "Extracting recordings from $timitdir/test"
+    test_recordings = timit_recordings(joinpath(timitdir, "test"); fmt=audio_fmt)
+    recordings = merge(train_recordings, test_recordings)
+
+    manifestpath = joinpath(dir, "recordings.jsonl")
+    open(manifestpath, "a") do f
+        writemanifest(f, recordings)
+    end
+
+    # Annotations
+    @info "Extracting annotations from $timitdir/train"
+    train_annotations = timit_annotations(joinpath(timitdir, "train"))
+    @info "Extracting annotations from $timitdir/test"
+    test_annotations = timit_annotations(joinpath(timitdir, "test"))
+    annotations = merge(train_annotations, test_annotations)
+
+
+    train_annotations = filter(annotations) do (k, v)
+        stype = v.data["sentence type"]
+        spk = v.data["speaker"]
+        (
+            (stype == "compact" || stype == "diverse") &&
+            spk ∈ TIMIT_TRAIN_SPK_LIST
+        )
+    end
+
+    dev_annotations = filter(annotations) do (k, v)
+        stype = v.data["sentence type"]
+        spk = v.data["speaker"]
+        (
+            (stype == "compact" || stype == "diverse") &&
+            spk ∈ TIMIT_DEV_SPK_LIST
+        )
+    end
+
+    test_annotations = filter(annotations) do (k, v)
+        stype = v.data["sentence type"]
+        spk = v.data["speaker"]
+        (
+            (stype == "compact" || stype == "diverse") &&
+            spk ∈ TIMIT_TEST_SPK_LIST
+        )
+    end
+
+    for (x, y) in ("train" => train_annotations,
+                   "dev" => dev_annotations,
+                   "test" => test_annotations)
+        manifestpath = joinpath(dir, "annotations-$(x).jsonl")
+        @info "Creating $manifestpath"
 
-        # Annotations
-        manifestpath = joinpath(dir, "annotations-$(subset).jsonl")
-        @debug "Preparing $manifestpath"
-        annotations = timit_annotations(sdir)
         open(manifestpath, "w") do f
-            writemanifest(f, annotations)
+            writemanifest(f, y)
         end
     end
 end
@@ -289,41 +337,48 @@ function timit_annotations(dir)
     splitline(line) = rsplit(line, limit=3)
 
     annotations = Dict()
-    tuple_ids = String[]
+    processed = Set()
 
     for (root, subdirs, files) in walkdir(dir)
         for file in files
             name, ext = splitext(file)
             _, dialect, spk = rsplit(root, "/", limit=3)
-            idtuple = join((dialect, spk, name), "/")
-
-            # Annotation files already processed (".wrd" and ".phn") 
-            if (idtuple in tuple_ids) && continue end
-            push!(tuple_ids, idtuple)
-            
-            words = name * ".wrd"  
-            phones = name * ".phn"
-            wpath = joinpath(root, words)
-            ppath = joinpath(root, phones)
-            
-            id = "timit_$(spk)_$(name)"
 
-            # Words 
-            wlines = map(splitline, eachline(wpath))
-            starts, ends, words = zip(wlines...)
-            start_ts = parse(Int, first(starts)) / 16000
-            end_ts = parse(Int, last(ends)) / 16000
-            dur = end_ts - start_ts
+            # Annotation files already processed (".wrd" and ".phn")
+            idtuple = (dialect, spk, name)
+            (idtuple in processed) && continue
+            push!(processed, (dialect, spk, name))
+
+            # Words
+            wpath = joinpath(root, name * ".wrd")
+            words = [last(split(line)) for line in eachline(wpath)]
 
             # Phones
-            plines = map(splitline, eachline(ppath))
-            pstarts, pends, phones = zip(plines...)
-            palign = [(parse(Int, s), parse(Int, e), TIMIT_PHONE_MAP48[p]) for (s, e, p) in zip(pstarts, pends, phones)]
-            
+            ppath = joinpath(root, name * ".phn")
+            palign = Tuple{Int,Int,String}[]
+            for line in eachline(ppath)
+                t0, t1, p = split(line)
+                push!(palign, (parse(Int, t0), parse(Int, t1), String(p)))
+            end
+
+            sentence_type = if startswith(name, "sa")
+                "dialect"
+            elseif startswith(name, "sx")
+                "compact"
+            else # startswith(name, "si")
+                "diverse"
+            end
+
+            id = "timit_$(spk)_$(name)"
             annotations[id] = Annotation(
-                id, id, start_ts, dur, [1],
+                id,  # recording id and annotation id are the same since we have
+                id,  # a one-to-one mapping
+                -1,  # start and duration is -1 means that we take the whole
+                -1,  # recording
+                [1], # only 1 channel (mono recording)
                 Dict(
                      "text" => join(words, " "),
+                     "sentence type" => sentence_type,
                      "alignment" => palign,
                      "dialect" => dialect,
                      "speaker" => spk,

src/dataset.jl

@@ -57,3 +57,10 @@ Base.getindex(d::SpeechDataset, idxs::AbstractVector) = map(Base.Fix1(getindex,
 
 Base.length(d::SpeechDataset) = length(d.idxs)
 
+function Base.filter(fn, d::SpeechDataset)
+    fidxs = filter(fn, d.idxs)
+    fannotations = filter(k_v -> fn(first(k_v)), d.annotations)
+    frecs = filter(k_v -> fn(first(k_v)), d.recordings)
+    SpeechDataset(fidxs, fannotations, frecs, :custom)
+end
+