Konferans bildirisi Açık Erişim
Zubari, Unal; Ozan, Ezgi Can; Acar, Banu Oskay; Ciloglu, Tolga; Esen, Ersin; Ates, Tugrul K.; Onur, Duygu Oskay
{ "conceptdoi": "10.81043/aperta.92904", "conceptrecid": "92904", "created": "2021-03-16T12:41:05.008183+00:00", "doi": "10.81043/aperta.92905", "files": [ { "bucket": "2181a27f-9261-4bbe-8651-66be9290c1dd", "checksum": "md5:8b97a08e268a47179dc0ea9d801acb76", "key": "bib-a2d37fe5-c5aa-4581-9110-d4f29c74467e.txt", "links": { "self": "https://aperta.ulakbim.gov.tr/api/files/2181a27f-9261-4bbe-8651-66be9290c1dd/bib-a2d37fe5-c5aa-4581-9110-d4f29c74467e.txt" }, "size": 177, "type": "txt" } ], "id": 92905, "links": { "badge": "https://aperta.ulakbim.gov.tr/badge/doi/10.81043/aperta.92905.svg", "bucket": "https://aperta.ulakbim.gov.tr/api/files/2181a27f-9261-4bbe-8651-66be9290c1dd", "conceptbadge": "https://aperta.ulakbim.gov.tr/badge/doi/10.81043/aperta.92904.svg", "conceptdoi": "https://doi.org/10.81043/aperta.92904", "doi": "https://doi.org/10.81043/aperta.92905", "html": "https://aperta.ulakbim.gov.tr/record/92905", "latest": "https://aperta.ulakbim.gov.tr/api/records/92905", "latest_html": "https://aperta.ulakbim.gov.tr/record/92905" }, "metadata": { "access_right": "open", "access_right_category": "success", "communities": [ { "id": "tubitak-adresli-yayinlar" } ], "creators": [ { "affiliation": "TUBITAK UZAY, Video & Audio Proc Grp, TR-06531 Ankara, Turkey", "name": "Zubari, Unal" }, { "name": "Ozan, Ezgi Can" }, { "affiliation": "TUBITAK UZAY, Video & Audio Proc Grp, TR-06531 Ankara, Turkey", "name": "Acar, Banu Oskay" }, { "affiliation": "METU, Dept Elect & Elect Engn, TR-06531 Ankara, Turkey", "name": "Ciloglu, Tolga" }, { "affiliation": "TUBITAK UZAY, Video & Audio Proc Grp, TR-06531 Ankara, Turkey", "name": "Esen, Ersin" }, { "name": "Ates, Tugrul K." }, { "affiliation": "TUBITAK UZAY, Video & Audio Proc Grp, TR-06531 Ankara, Turkey", "name": "Onur, Duygu Oskay" } ], "description": "Speech boundary detection contributes to performance of speech based applications such as speech recognition and speaker recognition. Speech boundary detector implemented in this study works on broadcast audio as a pre-processor module of a keyword spotter. Speech boundary detection is handled in 3 steps. At first step, audio data is segmented into homogeneous regions in an unsupervised manner. After an ACTIVITY/NON-ACTIVITY decision is made for each region, ACTIVITY regions are classified as Speech/Non-speech via Gaussian Mixture Model (GMM) based classification. GMM's are trained using a novel feature, Spectral Flow Direction (SFD), and an improved multi-band harmonicity feature in addition to widely used Mel Frequency Cepstral Coefficients (MFCC's).", "doi": "10.81043/aperta.92905", "has_grant": false, "license": { "id": "cc-by" }, "meeting": { "title": "18TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO-2010)" }, "publication_date": "2010-01-01", "related_identifiers": [ { "identifier": "10.81043/aperta.92904", "relation": "isVersionOf", "scheme": "doi" } ], "relations": { "version": [ { "count": 1, "index": 0, "is_last": true, "last_child": { "pid_type": "recid", "pid_value": "92905" }, "parent": { "pid_type": "recid", "pid_value": "92904" } } ] }, "resource_type": { "subtype": "conferencepaper", "title": "Konferans bildirisi", "type": "publication" }, "title": "SPEECH DETECTION ON BROADCAST AUDIO" }, "owners": [ 1 ], "revision": 1, "stats": { "downloads": 10.0, "unique_downloads": 10.0, "unique_views": 28.0, "version_downloads": 10.0, "version_unique_downloads": 10.0, "version_unique_views": 28.0, "version_views": 29.0, "version_volume": 1770.0, "views": 29.0, "volume": 1770.0 }, "updated": "2021-03-16T12:41:05.060479+00:00" }
Görüntülenme | 29 |
İndirme | 10 |
Veri hacmi | 1.8 kB |
Tekil görüntülenme | 28 |
Tekil indirme | 10 |