VOICE RECOGNIZER

PROBLEM TO BE SOLVED: To provide a voice recognizer which improves voice recognition performance while specifying an utterer. SOLUTION: The voice recognizer 100 for recognizing the voice emitted by the utterer includes an utterer specifying means 11 for specifying the utterer, and a voice recognitio...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	TAKEUCHI SHOJIRO, SEKINE YOSHIKAZU, SEKIYAMA HIROAKI
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 recognizer which improves voice recognition performance while specifying an utterer. SOLUTION: The voice recognizer 100 for recognizing the voice emitted by the utterer includes an utterer specifying means 11 for specifying the utterer, and a voice recognition characteristic adjustment means 12 for adjusting the voice recognition characteristics according to the specified utterer. The voice recognition characteristic adjustment means 12 is adapted to change over microphone sensitivity, frequency band eliminated by a voice range filter, a dialect recognition dictionary or frequency appearance recognition dictionary according to the specified utterer. The voice recognizer 100 is equipped with a voice recognition means 10 for acquiring voiceprint data from the voice, and the utterer specifying means 11 specifies the utterer by collating the preregistered voiceprint data with the voiceprint data acquired by the voice recognition means 10. COPYRIGHT: (C)2009,JPO&INPIT