VOICE DATA REPEATING DEVICE, TERMINAL, VOICE DATA REPEATING METHOD, AND VOICE RECOGNITION SYSTEM

PROBLEM TO BE SOLVED: To provide a voice recognition system with stable quality.SOLUTION: A voice data repeating device 110 transmits voice data for evaluation to a voice recognition server 104 after performing noise suppression processing in a noise suppression module 118, and receives a recognitio...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	HONMA TAKESHI, OBUCHI YASUNARI
Format:	Patent
Sprache:	eng
Schlagworte:	ACOUSTICS 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!

Beschreibung
Zusammenfassung:	PROBLEM TO BE SOLVED: To provide a voice recognition system with stable quality.SOLUTION: A voice data repeating device 110 transmits voice data for evaluation to a voice recognition server 104 after performing noise suppression processing in a noise suppression module 118, and receives a recognition result in order to check change of voice recognition performance of the voice recognition server 104 when an on-vehicle terminal 102 and the voice recognition server 104 are repeated. Then, the voice data repeating device 110 sets values of a parameter for noise suppression, which is used for the noise suppression processing and a parameter for result integration, which is used for integration processing of a plurality of recognition results obtained from the voice recognition server 104 to the optimal values based on the recognition result of the voice recognition server 104. Thus, an appropriate parameter is set even when the voice recognition performance of the voice recognition server 104 changes.