Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

 
 
DownloadE-Mail
  Information encoding by deep neural networks: what can we learn?

Ten Bosch, L., & Boves, L. (2018). Information encoding by deep neural networks: what can we learn? In Proceedings of Interspeech 2018 (pp. 1457-1461). doi:10.21437/Interspeech.2018-1896.

Item is

Basisdaten

einblenden: ausblenden:
Genre: Konferenzbeitrag

Dateien

einblenden: Dateien
ausblenden: Dateien
:
TenBosch_Boves_2018_Information encoding by deep neural networks.pdf (Verlagsversion), 523KB
Name:
TenBosch_Boves_2018_Information encoding by deep neural networks.pdf
Beschreibung:
-
OA-Status:
Sichtbarkeit:
Öffentlich
MIME-Typ / Prüfsumme:
application/pdf / [MD5]
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-
Lizenz:
-

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Ten Bosch, Louis1, 2, Autor           
Boves, L.1, Autor
Affiliations:
1Centre for Language Studies, Radboud University, ou_55238              
2Other Research, MPI for Psycholinguistics, Max Planck Society, Nijmegen, NL, ou_55217              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: The recent advent of deep learning techniques in speech tech-nology and in particular in automatic speech recognition hasyielded substantial performance improvements. This suggeststhat deep neural networks (DNNs) are able to capture structurein speech data that older methods for acoustic modeling, suchas Gaussian Mixture Models and shallow neural networks failto uncover. In image recognition it is possible to link repre-sentations on the first couple of layers in DNNs to structuralproperties of images, and to representations on early layers inthe visual cortex. This raises the question whether it is possi-ble to accomplish a similar feat with representations on DNNlayers when processing speech input. In this paper we presentthree different experiments in which we attempt to untanglehow DNNs encode speech signals, and to relate these repre-sentations to phonetic knowledge, with the aim to advance con-ventional phonetic concepts and to choose the topology of aDNNs more efficiently. Two experiments investigate represen-tations formed by auto-encoders. A third experiment investi-gates representations on convolutional layers that treat speechspectrograms as if they were images. The results lay the basisfor future experiments with recursive networks.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2018-10
 Publikationsstatus: Online veröffentlicht
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: Expertenbegutachtung
 Identifikatoren: DOI: 10.21437/Interspeech.2018-1896
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Interspeech 2018
Veranstaltungsort: Hyderabad, India
Start-/Enddatum: 2018-09-02 - 2018-09-06

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Proceedings of Interspeech 2018
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1457 - 1461 Identifikator: -