Título:
|
Visualizing punctuation restoration in speech transcripts with prosograph
|
Autor/a:
|
Öktem, Alp; Farrús, Mireia; Bonafonte, Antonio
|
Abstract:
|
Comunicació presentada a: Interspeech 2018, celebrat del 2 al 6 de setembre de 2018 a Hyderabad, Índia. |
Abstract:
|
We have developed a neural architecture that tests the effect
of lexical, morphosyntactic and prosodic features in restoring
punctuation in speech transcriptions. Having outperformed a
baseline model in terms of precision and recall, we further extend
our performance tests by attaching it in a speech recognition
pipeline. The visual and interactive testing environment
that we prepared helps us observe how our models generalizes
in unseen data and also plan our next steps for improvement. |
Abstract:
|
The first author has received Maria de Maeztu Reproducibility
Award from Department of Information and Communication
Technologies of Universitat Pompeu Fabra in 2018 through
presentation of this work. The second author is funded by the
Spanish Ministry of Economy, Industry and Competitiveness
through the Ram´on y Cajal program. |
Materia(s):
|
-Prosody -Punctuation -Automatic speech recognition |
Derechos:
|
© 2018 ISCA
|
Tipo de documento:
|
Objeto de conferencia Artículo - Versión publicada |
Editor:
|
International Speech Communication Association (ISCA)
|
Compartir:
|
|