Multimodal based punctuation and/or casing prediction

Techniques for predicting punctuation and casing using multimodal fusion are described. An exemplary method includes processing generated text by: tokenizing the generated text into sub-words, and generating a sequence of lexical features for the sub-words using a pre-trained lexical encoder; proces...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Bodapati, Sravan Babu, Bekal Kannangola, Dhanush, Kirchhoff, Katrin, Sunkara, Monica Lakshmi, Ronanki, Srikanth
Format:	Patent
Sprache:	eng
Schlagworte:	ACOUSTICS CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!