Changes

On December 3, 2024 at 9:18:17 AM UTC, admin:
Changed title to Speech Commands Dataset (previously Speech Commands dataset)
Set author of Speech Commands Dataset to Pete Warden (previously Albert Gu)
Updated description of Speech Commands Dataset from
The dataset used in this paper is the Speech Commands dataset, which contains raw audio segments of length up to 16000, split into 84843 train and 11005 test segments.
to
The dataset used for training the keyword spotting model is the ESC: Dataset for Environmental Sound Classification, and the Speech Commands Dataset.
Removed the following tags from Speech Commands Dataset
Added the following tags to Speech Commands Dataset
Changed value of field defined_in to https://doi.org/10.48550/arXiv.1911.08644 in Speech Commands Dataset
Changed value of field citation to ['https://doi.org/10.48550/arXiv.2102.02611', 'https://doi.org/10.48550/arXiv.1911.12482'] in Speech Commands Dataset
Deleted resource Original Metadata from Speech Commands Dataset
              
    
          
          
        
        
            f 1 { f 1 {
            2   "access_rights": "", 2   "access_rights": "",
            n 3   "author": "Albert Gu", n 3   "author": "Pete Warden",
            4   "author_email": "", 4   "author_email": "",
            5   "citation": [ 5   "citation": [
            n n 6     "https://doi.org/10.48550/arXiv.2102.02611",
            6     "https://doi.org/10.48550/arXiv.1911.10182", 7     "https://doi.org/10.48550/arXiv.1911.12482"
            7     "https://doi.org/10.48550/arXiv.2303.11249" 
            8   ], 8   ],
            9   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", 9   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            n 10   "defined_in": "https://doi.org/10.1109/AICAS54282.2022.9869920", n 10   "defined_in": "https://doi.org/10.48550/arXiv.1911.08644",
            11   "doi": "10.57702/ta2ci6v4", 11   "doi": "10.57702/ta2ci6v4",
            12   "doi_date_published": "2024-12-02", 12   "doi_date_published": "2024-12-02",
            13   "doi_publisher": "TIB", 13   "doi_publisher": "TIB",
            14   "doi_status": true, 14   "doi_status": true,
            15   "domain": "https://service.tib.eu/ldmservice", 15   "domain": "https://service.tib.eu/ldmservice",
            n 16   "extra_authors": [ n 
            17     { 
            18       "extra_author": "Karan Goel", 
            19       "orcid": "" 
            20     }, 
            21     { 
            22       "extra_author": "Christopher R\u00b4e", 
            23       "orcid": "" 
            24     } 
            25   ], 
            26   "groups": [ 16   "groups": [
            27     { 17     {
            28       "description": "", 18       "description": "",
            n 29       "display_name": "Audio Data", n 19       "display_name": "Audio Classification",
            30       "id": "a9a9163f-d5b3-466a-8011-65241e6f311d", 20       "id": "51657985-b505-47eb-9ccc-cca0bd9c58ac",
            31       "image_display_url": "", 21       "image_display_url": "",
            n 32       "name": "audio-data", n 
            33       "title": "Audio Data" 
            34     }, 
            35     { 
            36       "description": "", 
            37       "display_name": "Image Classification", 
            38       "id": "18b77292-26aa-4caf-89ed-cbd35fa60474", 
            39       "image_display_url": "", 
            40       "name": "image-classification", 22       "name": "audio-classification",
            41       "title": "Image Classification" 23       "title": "Audio Classification"
            42     }, 24     },
            43     { 25     {
            44       "description": "", 26       "description": "",
            45       "display_name": "Speech Recognition", 27       "display_name": "Speech Recognition",
            46       "id": "78414f7c-330f-49b5-bf33-40f8c2ac4928", 28       "id": "78414f7c-330f-49b5-bf33-40f8c2ac4928",
            47       "image_display_url": "", 29       "image_display_url": "",
            48       "name": "speech-recognition", 30       "name": "speech-recognition",
            49       "title": "Speech Recognition" 31       "title": "Speech Recognition"
            n 50     }, n 
            51     { 
            52       "description": "", 
            53       "display_name": "Text Sentiment Analysis", 
            54       "id": "33f16bcc-4003-4223-a1bd-0eeeec0b65a3", 
            55       "image_display_url": "", 
            56       "name": "text-sentiment-analysis", 
            57       "title": "Text Sentiment Analysis" 
            58     } 32     }
            59   ], 33   ],
            60   "id": "dcc10abf-c262-499f-b81a-a5b4edf6088b", 34   "id": "dcc10abf-c262-499f-b81a-a5b4edf6088b",
            61   "isopen": false, 35   "isopen": false,
            62   "landing_page": "https://arxiv.org/abs/1804.03209", 36   "landing_page": "https://arxiv.org/abs/1804.03209",
            63   "license_title": null, 37   "license_title": null,
            64   "link_orkg": "", 38   "link_orkg": "",
            65   "metadata_created": "2024-12-02T18:10:52.270831", 39   "metadata_created": "2024-12-02T18:10:52.270831",
            n 66   "metadata_modified": "2024-12-02T18:10:52.828738", n 40   "metadata_modified": "2024-12-03T09:18:16.414838",
            67   "name": "speech-commands-dataset", 41   "name": "speech-commands-dataset",
            n 68   "notes": "The dataset used in this paper is the Speech Commands  n 42   "notes": "The dataset used for training the keyword spotting model 
            69 dataset, which contains raw audio segments of length up to 16000,  43 is the ESC: Dataset for Environmental Sound Classification, and the 
            70 split into 84843 train and 11005 test segments.", 44 Speech Commands Dataset.",
            71   "num_resources": 1, 45   "num_resources": 0,
            72   "num_tags": 11, 46   "num_tags": 7,
            73   "organization": { 47   "organization": {
            74     "approval_status": "approved", 48     "approval_status": "approved",
            75     "created": "2024-11-25T12:11:38.292601", 49     "created": "2024-11-25T12:11:38.292601",
            76     "description": "", 50     "description": "",
            77     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", 51     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            78     "image_url": "", 52     "image_url": "",
            79     "is_organization": true, 53     "is_organization": true,
            80     "name": "no-organization", 54     "name": "no-organization",
            81     "state": "active", 55     "state": "active",
            82     "title": "No Organization", 56     "title": "No Organization",
            83     "type": "organization" 57     "type": "organization"
            84   }, 58   },
            85   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", 59   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            86   "private": false, 60   "private": false,
            87   "relationships_as_object": [], 61   "relationships_as_object": [],
            88   "relationships_as_subject": [], 62   "relationships_as_subject": [],
            n 89   "resources": [ n 63   "resources": [],
            90     { 
            91       "cache_last_updated": null, 
            92       "cache_url": null, 
            93       "created": "2024-12-02T18:38:42", 
            94       "data": [ 
            95         "dcterms:title", 
            96         "dcterms:accessRights", 
            97         "dcterms:creator", 
            98         "dcterms:description", 
            99         "dcterms:issued", 
            100         "dcterms:language", 
            101         "dcterms:identifier", 
            102         "dcat:theme", 
            103         "dcterms:type", 
            104         "dcat:keyword", 
            105         "dcat:landingPage", 
            106         "dcterms:hasVersion", 
            107         "dcterms:format", 
            108         "mls:task", 
            109         "datacite:isDescribedBy" 
            110       ], 
            111       "description": "The json representation of the dataset with its  
            112 distributions based on DCAT.", 
            113       "format": "JSON", 
            114       "hash": "", 
            115       "id": "1bb0e275-f665-4a71-9561-f9753d49ee3b", 
            116       "last_modified": "2024-12-02T18:10:52.820762", 
            117       "metadata_modified": "2024-12-02T18:10:52.831499", 
            118       "mimetype": "application/json", 
            119       "mimetype_inner": null, 
            120       "name": "Original Metadata", 
            121       "package_id": "dcc10abf-c262-499f-b81a-a5b4edf6088b", 
            122       "position": 0, 
            123       "resource_type": null, 
            124       "size": 1142, 
            125       "state": "active", 
            126       "url":  
            127 resource/1bb0e275-f665-4a71-9561-f9753d49ee3b/download/metadata.json", 
            128       "url_type": "upload" 
            129     } 
            130   ], 
            131   "services_used_list": "", 64   "services_used_list": "",
            132   "state": "active", 65   "state": "active",
            133   "tags": [ 66   "tags": [
            134     { 67     {
            n 135       "display_name": "Audio", n 68       "display_name": "Audio Classification",
            136       "id": "f74406d3-acd1-4ba7-b068-c5ffb6c9bb87", 69       "id": "b22a7882-7ce7-4d1a-ac4d-79d6392b6530",
            137       "name": "Audio", 70       "name": "Audio Classification",
            138       "state": "active", 71       "state": "active",
            139       "vocabulary_id": null 72       "vocabulary_id": null
            140     }, 73     },
            141     { 74     {
            n 142       "display_name": "Commands", n 75       "display_name": "Audio Recordings",
            143       "id": "fb71f168-be4b-41a7-b00a-792b0fb5189e", 76       "id": "900d14a1-4863-47d4-894b-e803b8083e31",
            144       "name": "Commands", 77       "name": "Audio Recordings",
            145       "state": "active", 78       "state": "active",
            146       "vocabulary_id": null 79       "vocabulary_id": null
            147     }, 80     },
            148     { 81     {
            n 149       "display_name": "Image Classification", n 82       "display_name": "Speech Recognition",
            150       "id": "418e2ddf-a1d3-42ac-ad05-156f79ca8e22", 83       "id": "eebd420b-8b14-4294-ade4-4917392439bf",
            151       "name": "Image Classification", 84       "name": "Speech Recognition",
            152       "state": "active", 85       "state": "active",
            153       "vocabulary_id": null 86       "vocabulary_id": null
            154     }, 87     },
            155     { 88     {
            n 156       "display_name": "Sound Recognition", n 89       "display_name": "Spoken Words",
            157       "id": "c4cc6269-469c-4988-ab1a-e69b0699a3af", 90       "id": "5c4be6fd-4408-42ce-8a62-6bfdd3ad508f",
            158       "name": "Sound Recognition", 91       "name": "Spoken Words",
            159       "state": "active", 92       "state": "active",
            160       "vocabulary_id": null 93       "vocabulary_id": null
            161     }, 94     },
            162     { 95     {
            n 163       "display_name": "Speech", n 96       "display_name": "audio dataset",
            164       "id": "eeaa610e-2ccc-4a17-9291-21f99338b51a", 97       "id": "9be3970b-9220-4f97-9fa8-b3aa57425847",
            165       "name": "Speech", 98       "name": "audio dataset",
            166       "state": "active", 99       "state": "active",
            167       "vocabulary_id": null 100       "vocabulary_id": null
            168     }, 101     },
            169     { 102     {
            n 170       "display_name": "Speech Commands", n 103       "display_name": "keyword spotting",
            171       "id": "18db748c-c0b8-4a0c-a6c6-f2b1499a0a0c", 104       "id": "0ab117c8-ade7-4b2d-bed0-61b49ae535fa",
            172       "name": "Speech Commands", 105       "name": "keyword spotting",
            173       "state": "active", 
            174       "vocabulary_id": null 
            175     }, 
            176     { 
            177       "display_name": "Text Sentiment Analysis", 
            178       "id": "f18259df-9360-408a-ac72-247f2639168a", 
            179       "name": "Text Sentiment Analysis", 
            180       "state": "active", 
            181       "vocabulary_id": null 
            182     }, 
            183     { 
            184       "display_name": "limited-vocabulary speech recognition", 
            185       "id": "de6b2001-b099-40ad-a0b5-2459b7d6e852", 
            186       "name": "limited-vocabulary speech recognition", 
            187       "state": "active", 
            188       "vocabulary_id": null 
            189     }, 
            190     { 
            191       "display_name": "speech commands", 
            192       "id": "476fd66d-7ac7-490f-86de-017b44198a66", 
            193       "name": "speech commands", 
            194       "state": "active", 106       "state": "active",
            195       "vocabulary_id": null 107       "vocabulary_id": null
            196     }, 108     },
            197     { 109     {
            198       "display_name": "speech recognition", 110       "display_name": "speech recognition",
            199       "id": "84f7ed93-69f7-4690-99f1-fa82a8fb4110", 111       "id": "84f7ed93-69f7-4690-99f1-fa82a8fb4110",
            200       "name": "speech recognition", 112       "name": "speech recognition",
            201       "state": "active", 113       "state": "active",
            202       "vocabulary_id": null 114       "vocabulary_id": null
            n 203     }, n 
            204     { 
            205       "display_name": "spoken english", 
            206       "id": "46172b9d-d2f8-4d5b-a97c-f612520279cd", 
            207       "name": "spoken english", 
            208       "state": "active", 
            209       "vocabulary_id": null 
            210     } 115     }
            211   ], 116   ],
            t 212   "title": "Speech Commands dataset", t 117   "title": "Speech Commands Dataset",
            213   "type": "dataset", 118   "type": "dataset",
            214   "version": "" 119   "version": ""
            215 } 120 }