Speech recognition text processing method and device and electronic equipment

The invention discloses a speech recognition text processing method and device, electronic equipment and a computer readable medium. The method comprises the following steps: acquiring a first text obtained by recognizing the speech of a user; and inputting the first text into a trained text process...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: ZHENG YUANZHONG
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a speech recognition text processing method and device, electronic equipment and a computer readable medium. The method comprises the following steps: acquiring a first text obtained by recognizing the speech of a user; and inputting the first text into a trained text processing model, wherein the training data used by the text processing model is labeled with phoneme information, the text processing model comprises a convolutional neural network and a gating circulation unit, the convolutional neural network is used for extracting features of the first text according to the phoneme information of the first text, and the gating circulation unit is used for generating a second text according to the features of the first text as a voice recognition result. The processing model combining the convolutional neural network and the gating loop unit is adopted, the convolutional neural network is suitable for accurately and rapidly extracting deep features capable of reflecting phoneme charact