Commit 45f06fd0 authored by Vladimir Malenovsky's avatar Vladimir Malenovsky
Browse files

correction of categories per talker/talker pairs in ISM1 and ISM2 tests

parent c9fbdb5d
Loading
Loading
Loading
Loading
Loading
+246 −247
Original line number Diff line number Diff line
@@ -86,339 +86,338 @@ use_output_prefix: "leee"


scenes:
    a1: 
        name: "a1s01"
    cat1_1: 
        name: "cat1/a1s01.wav"
        description: "Talker sitting at a table"
        source: ["m1s01.wav", "m1s07.wav"]
        azimuth: 0 
        elevation: 0 
        overlap: -0.5
        
    a2: 
        name: "a6s02"
        description: "Talker sitting at a table"
        source: ["f3s02.wav", "f3s08.wav"]
        azimuth: 60 
    cat1_2: 
        name: "cat1/a1s02.wav"
        description: "Standing talker."
        source: ["m1s02.wav", "m1s08.wav"]
        azimuth: 180 
        elevation: 35 
        overlap: -0.5

    cat1_3: 
        name: "cat1/a1s03.wav"
        description: "Smaller talker (child) walking around a table."
        source: ["m1s03.wav", "m1s09.wav"]
        azimuth: "120:1:120+360" 
        elevation: 0 
        overlap: -0.5

    a3: 
        name: "a5s03"
        description: "Talker sitting at a table"
        source: ["m3s03.wav", "m3s09.wav"]
    cat1_4: 
        name: "cat1/a1s04.wav"
        description: "Talker walking around the table."
        source: ["m1s04.wav", "m1s10.wav"]
        azimuth: "180:-1:180-360" 
        elevation: 35 
        overlap: -0.5

    cat1_5: 
        name: "cat1/a1s05.wav"
        description: "Elevation displacement."
        source: ["m1s05.wav", "m1s11.wav"]
        azimuth: 120 
        elevation: 0 
        elevation: "-90:0.5:90"  
        overlap: -0.5

    a4: 
        name: "a4s04"
        description: "Talker sitting at a table"
        source: ["f2s04.wav", "f2s10.wav"]
    cat1_6: 
        name: "cat1/a1s06.wav"
        description: "Azimuth and elevation displacement."
        source: ["m1s06.wav", "m1s12.wav"]
        azimuth: "0:0.5:0+180" 
        elevation: "35:-0.2:-35" 
        overlap: -0.5
        
    cat1_7:
        name: "cat1/a1s07.wav"
        description: "Preliminary: Standing talker."
        source: ["m1s13.wav", "m1s14.wav"]
        azimuth: 180 
        elevation: 0 
        elevation: 35 
        overlap: -0.5        

    a5: 
        name: "a3s05"
        description: "Talker sitting at a table"
        source: ["m2s05.wav", "m2s11.wav"]
        azimuth: 240 
    cat2_1: 
        name: "cat2/a2s01.wav"
        description: "Standing talker."
        source: ["f1s01.wav", "f1s07.wav"]
        azimuth: 120 
        elevation: 35 
        overlap: -0.5

    cat2_2: 
        name: "cat2/a2s02.wav"
        description: "Smaller talker (child) walking around a table."
        source: ["f1s02.wav", "f1s08.wav"]
        azimuth: "60:1:60+360" 
        elevation: 0 
        overlap: -0.5

    a6: 
        name: "a2s06"
    cat2_3: 
        name: "cat2/a2s03.wav"
        description: "Talker walking around the table."
        source: ["f1s03.wav", "f1s09.wav"]
        azimuth: "120:-1:120-360" 
        elevation: 35 
        overlap: -0.5

    cat2_4: 
        name: "cat2/a2s04.wav"
        description: "Elevation displacement."
        source: ["f1s04.wav", "f1s10.wav"]
        azimuth: 60 
        elevation: "-90:0.5:90"  
        overlap: -0.5

    cat2_5: 
        name: "cat2/a2s05.wav"
        description: "Azimuth and elevation displacement."
        source: ["f1s05.wav", "f1s11.wav"]
        azimuth: "300:0.5:300+180" 
        elevation: "35:-0.2:-35" 
        overlap: -0.5

    cat2_6: 
        name: "cat2/a2s06.wav"
        description: "Talker sitting at a table"
        source: ["f1s06.wav", "f1s12.wav"]
        azimuth: 300 
        elevation: 0 
        overlap: -0.5
        
    a7: 
        name: "a2s07"
    cat2_7: 
        name: "cat2/a2s07.wav"
        description: "Preliminary: Talker sitting at a table"
        source: ["f1s13.wav", "f1s14.wav"]
        azimuth: 0 
        elevation: 0 
        overlap: -0.5        

    b1: 
        name: "a2s01"
        description: "Standing talker."
        source: ["f1s01.wav", "f1s07.wav"]
        azimuth: 120 
        elevation: 35 
    cat3_1: 
        name: "cat3/a3s01.wav"
        description: "Smaller talker (child) walking around a table."
        source: ["m2s01.wav", "m2s07.wav"]
        azimuth: "0:1:360"
        elevation: 0 
        overlap: -0.5

    b2: 
        name: "a1s02"
        description: "Standing talker."
        source: ["m1s02.wav", "m1s08.wav"]
        azimuth: 180 
    cat3_2: 
        name: "cat3/a3s02.wav"
        description: "Talker walking around the table."
        source: ["m2s02.wav", "m2s08.wav"]
        azimuth: "60:-1:60-360" 
        elevation: 35 
        overlap: -0.5

    b3: 
        name: "a6s03"
        description: "Standing talker."
        source: ["f3s03.wav", "f3s09.wav"]
        azimuth: 240 
        elevation: 35 
    cat3_3: 
        name: "cat3/a3s03.wav"
        description: "Elevation displacement."
        source: ["m2s03.wav", "m2s09.wav"]
        azimuth: 0 
        elevation: "-90:0.5:90"  
        overlap: -0.5

    b4: 
        name: "a5s04"
        description: "Standing talker."
        source: ["m3s04.wav", "m3s10.wav"]
        azimuth: 300 
        elevation: 35 
    cat3_4: 
        name: "cat3/a3s04.wav"
        description: "Azimuth and elevation displacement."
        source: ["m2s04.wav", "m2s10.wav"]
        azimuth: "240:0.5:240+180" 
        elevation: "35:-0.2:-35"
        overlap: -0.5

    b5: 
        name: "a4s05"
        description: "Standing talker."
        source: ["f2s05.wav", "f2s11.wav"]
        azimuth: 0 
        elevation: 35 
    cat3_5: 
        name: "cat3/a3s05.wav"
        description: "Talker sitting at a table"
        source: ["m2s05.wav", "m2s11.wav"]
        azimuth: 240 
        elevation: 0 
        overlap: -0.5

    b6: 
        name: "a3s06"
    cat3_6: 
        name: "cat3/a3s06.wav"
        description: "Standing talker."
        source: ["m2s06.wav", "m2s12.wav"]
        azimuth: 60 
        elevation: 35 
        overlap: -0.5
        
    b7:
        name: "a1s07"
        description: "Preliminary: Standing talker."
        source: ["m1s13.wav", "m1s14.wav"]
        azimuth: 180 
    cat3_7:
        name: "cat3/a3s07.wav"
        description: "Preliminary: Talker walking around the table."
        source: ["m2s13.wav", "m2s14.wav"]
        azimuth: "180:-1:180-360" 
        elevation: 35 
        overlap: -0.5

    c1: 
        name: "a3s01"
        description: "Smaller talker (child) walking around a table."
        source: ["m2s01.wav", "m2s07.wav"]
        azimuth: "0:1:360"
        elevation: 0 
    cat4_1: 
        name: "cat4/a4s01.wav"
        description: "Talker walking around the table."
        source: ["f2s01.wav", "f2s07.wav"]
        azimuth: "0:-1:-360"
        elevation: 35 
        overlap: -0.5

    c2: 
        name: "a2s02"
        description: "Smaller talker (child) walking around a table."
        source: ["f1s02.wav", "f1s08.wav"]
        azimuth: "60:1:60+360" 
    cat4_2: 
        name: "cat4/a4s02.wav"
        description: "Elevation displacement."
        source: ["f2s02.wav", "f2s08.wav"]
        azimuth: 300 
        elevation: 0 
        overlap: -0.5

    c3: 
        name: "a1s03"
        description: "Smaller talker (child) walking around a table."
        source: ["m1s03.wav", "m1s09.wav"]
        azimuth: "120:1:120+360" 
        elevation: 0 
    cat4_3: 
        name: "cat4/a4s03.wav"
        description: "Azimuth and elevation displacement."
        source: ["f2s03.wav", "f2s09.wav"]
        azimuth: "180:0.5:180+180" 
        elevation: "35:-0.2:-35" 
        overlap: -0.5

    c4: 
        name: "a6s04"
        description: "Smaller talker (child) walking around a table."
        source: ["f3s04.wav", "f3s10.wav"]
        azimuth: "180:1:180+360" 
    cat4_4: 
        name: "cat4/a4s04.wav"
        description: "Talker sitting at a table"
        source: ["f2s04.wav", "f2s10.wav"]
        azimuth: 180 
        elevation: 0 
        overlap: -0.5

    c5: 
        name: "a5s05"
        description: "Smaller talker (child) walking around a table."
        source: ["m3s05.wav", "m3s11.wav"]
        azimuth: "240:1:240+360"
        elevation: 0 
    cat4_5: 
        name: "cat4/a4s05.wav"
        description: "Standing talker."
        source: ["f2s05.wav", "f2s11.wav"]
        azimuth: 0 
        elevation: 35 
        overlap: -0.5

    c6: 
        name: "a4s06"
    cat4_6: 
        name: "cat4/a4s06.wav"
        description: "Smaller talker (child) walking around a table."
        source: ["f2s06.wav", "f2s12.wav"]
        azimuth: "300:1:300+360" 
        elevation: 0 
        overlap: -0.5
        
    c7:
        name: "a4s07"
    cat4_7:
        name: "cat4/a4s07.wav"
        description: "Preliminary: Smaller talker (child) walking around a table."
        source: ["f2s13.wav", "f2s14.wav"]
        azimuth: "120:1:120+360" 
        elevation: 0 
        overlap: -0.5        

    d1: 
        name: "a4s01"
        description: "Talker walking around the table."
        source: ["f2s01.wav", "f2s07.wav"]
        azimuth: "0:-1:-360"
        elevation: 35 
    cat5_1: 
        name: "cat5/a5s01.wav"
        description: "Elevation displacement."
        source: ["m3s01.wav", "m3s07.wav"]
        azimuth: 240 
        elevation: "-90:0.5:90" 
        overlap: -0.5

    d2: 
        name: "a3s02"
        description: "Talker walking around the table."
        source: ["m2s02.wav", "m2s08.wav"]
        azimuth: "60:-1:60-360" 
        elevation: 35 
    cat5_2: 
        name: "cat5/a5s02.wav"
        description: "Azimuth and elevation displacement."
        source: ["m3s02.wav", "m3s08.wav"]
        azimuth: "120:0.5:120+180" 
        elevation: "35:-0.2:-35" 
        overlap: -0.5

    d3: 
        name: "a2s03"
        description: "Talker walking around the table."
        source: ["f1s03.wav", "f1s09.wav"]
        azimuth: "120:-1:120-360" 
        elevation: 35 
    cat5_3: 
        name: "cat5/a5s03.wav"
        description: "Talker sitting at a table"
        source: ["m3s03.wav", "m3s09.wav"]
        azimuth: 120 
        elevation: 0 
        overlap: -0.5

    d4: 
        name: "a1s04"
        description: "Talker walking around the table."
        source: ["m1s04.wav", "m1s10.wav"]
        azimuth: "180:-1:180-360" 
    cat5_4: 
        name: "cat5/a5s04.wav"
        description: "Standing talker."
        source: ["m3s04.wav", "m3s10.wav"]
        azimuth: 300 
        elevation: 35 
        overlap: -0.5

    d5: 
        name: "a6s05"
        description: "Talker walking around the table."
        source: ["f3s05.wav", "f3s11.wav"]
        azimuth: "240:-1:240-360"
        elevation: 35 
    cat5_5: 
        name: "cat5/a5s05.wav"
        description: "Smaller talker (child) walking around a table."
        source: ["m3s05.wav", "m3s11.wav"]
        azimuth: "240:1:240+360"
        elevation: 0 
        overlap: -0.5

    d6: 
        name: "a5s06"
    cat5_6: 
        name: "cat5/a5s06.wav"
        description: "Talker walking around the table."
        source: ["m3s06.wav", "m3s12.wav"]
        azimuth: "300:-1:300-360" 
        elevation: 35
        overlap: -0.5
        
    d7:
        name: "a3s07"
        description: "Preliminary: Talker walking around the table."
        source: ["m2s13.wav", "m2s14.wav"]
        azimuth: "180:-1:180-360" 
        elevation: 35 
    cat5_7:
        name: "cat5/a5s07.wav"
        description: "Preliminary: Azimuth and elevation displacement."
        source: ["m3s13.wav", "m3s14.wav"]
        azimuth: "0:0.5:0+180" 
        elevation: "35:-0.2:-35" 
        overlap: -0.5        

    e1: 
        name: "a5s01"
        description: "Elevation displacement."
        source: ["m3s01.wav", "m3s07.wav"]
        azimuth: 240 
        elevation: "-90:0.5:90" 
    cat6_1: 
        name: "cat6/a6s01.wav"
        description: "Azimuth and elevation displacement."
        source: ["f3s01.wav", "f3s07.wav"]
        azimuth: "60:0.5:60+180" 
        elevation: "35:-0.2:-35"
        overlap: -0.5
        
    e2: 
        name: "a4s02"
        description: "Elevation displacement."
        source: ["f2s02.wav", "f2s08.wav"]
        azimuth: 300 
    cat6_2: 
        name: "cat6/a6s02.wav"
        description: "Talker sitting at a table"
        source: ["f3s02.wav", "f3s08.wav"]
        azimuth: 60 
        elevation: 0 
        overlap: -0.5
        
    e3: 
        name: "a3s03"
        description: "Elevation displacement."
        source: ["m2s03.wav", "m2s09.wav"]
        azimuth: 0 
        elevation: "-90:0.5:90"  
    cat6_3: 
        name: "cat6/a6s03.wav"
        description: "Standing talker."
        source: ["f3s03.wav", "f3s09.wav"]
        azimuth: 240 
        elevation: 35 
        overlap: -0.5

    e4: 
        name: "a2s04"
        description: "Elevation displacement."
        source: ["f1s04.wav", "f1s10.wav"]
        azimuth: 60 
        elevation: "-90:0.5:90"  
    cat6_4: 
        name: "cat6/a6s04.wav"
        description: "Smaller talker (child) walking around a table."
        source: ["f3s04.wav", "f3s10.wav"]
        azimuth: "180:1:180+360" 
        elevation: 0 
        overlap: -0.5

    e5: 
        name: "a1s05"
        description: "Elevation displacement."
        source: ["m1s05.wav", "m1s11.wav"]
        azimuth: 120 
        elevation: "-90:0.5:90"  
    cat6_5: 
        name: "cat6/a6s05.wav"
        description: "Talker walking around the table."
        source: ["f3s05.wav", "f3s11.wav"]
        azimuth: "240:-1:240-360"
        elevation: 35 
        overlap: -0.5

    e6: 
        name: "a6s06"
    cat6_6: 
        name: "cat6/a6s06.wav"
        description: "Elevation displacement."
        source: ["f3s06.wav", "f3s12.wav"]
        azimuth: 180 
        elevation: "-90:0.5:90"  
        overlap: -0.5

    e7:
        name: "a6s07"
    cat6_7:
        name: "cat6/a6s07.wav"
        description: "Preliminary: Elevation displacement."
        source: ["f3s13.wav", "f3s14.wav"]
        azimuth: 120 
        elevation: "-90:0.5:90"  
        overlap: -0.5
 
    f1: 
        name: "a6s01"
        description: "Azimuth and elevation displacement."
        source: ["f3s01.wav", "f3s07.wav"]
        azimuth: "60:0.5:60+180" 
        elevation: "35:-0.2:-35"
        overlap: -0.5
 
    f2: 
        name: "a5s02"
        description: "Azimuth and elevation displacement."
        source: ["m3s02.wav", "m3s08.wav"]
        azimuth: "120:0.5:120+180" 
        elevation: "35:-0.2:-35" 
        overlap: -0.5
  
    f3: 
        name: "a4s03"
        description: "Azimuth and elevation displacement."
        source: ["f2s03.wav", "f2s09.wav"]
        azimuth: "180:0.5:180+180" 
        elevation: "35:-0.2:-35" 
        overlap: -0.5
  
    f4: 
        name: "a3s04"
        description: "Azimuth and elevation displacement."
        source: ["m2s04.wav", "m2s10.wav"]
        azimuth: "240:0.5:240+180" 
        elevation: "35:-0.2:-35"
        overlap: -0.5
  
    f5: 
        name: "a2s05"
        description: "Azimuth and elevation displacement."
        source: ["f1s05.wav", "f1s11.wav"]
        azimuth: "300:0.5:300+180" 
        elevation: "35:-0.2:-35" 
        overlap: -0.5
  
    f6: 
        name: "a1s06"
        description: "Azimuth and elevation displacement."
        source: ["m1s06.wav", "m1s12.wav"]
        azimuth: "0:0.5:0+180" 
        elevation: "35:-0.2:-35" 
        overlap: -0.5

    f7:
        name: "a5s07"
        description: "Preliminary: Azimuth and elevation displacement."
        source: ["m3s13.wav", "m3s14.wav"]
        azimuth: "0:0.5:0+180" 
        elevation: "35:-0.2:-35" 
        overlap: -0.5
  
 No newline at end of file
+260 −260

File changed.

Preview size limit exceeded, changes collapsed.

+2 −2
Original line number Diff line number Diff line
@@ -334,8 +334,8 @@ def generate_ism1_scene(
    # write ISM metadata to the output file in .0.csv format
    csv_filename = os.path.join(
        cfg.output_path,
        "cat"+scene["name"][1],
        cfg.use_output_prefix + os.path.basename(scene["name"]) + ".wav.0.csv",
        os.path.dirname(scene["name"]),
        cfg.use_output_prefix + os.path.basename(scene["name"]) + ".0.csv",
    )

    with open(
+2 −2
Original line number Diff line number Diff line
@@ -378,8 +378,8 @@ def generate_ism2_scene(
        # generate .csv filename (should end with .0.csv, .1.csv, ...)
        csv_filename = os.path.join(
            cfg.output_path,
            "cat"+scene["name"][1],
            cfg.use_output_prefix + os.path.basename(scene["name"]) + f".wav.{i}.csv",
            os.path.dirname(scene["name"]),
            cfg.use_output_prefix + os.path.basename(scene["name"]) + f".{i}.csv",
        )

        with open(