Systeme de reconnaissance de mots et procede d'evaluation de clients et d'employes

Word recognition system and method for customer and employee assessment

Abstract

L'invention a trait à des comparaisons un à N de mots et/ou d'empreintes vocales d'appelants avec des mots et/ou des empreintes vocales connues, afin d'identifier d'éventuelles correspondances importantes entre eux. Lorsqu'un client communique avec une entité donnée, tel qu'un centre de service à la clientèle, le système selon l'invention réalise un enregistrement de l'appel en temps réel, qui contient à la fois la voix du client et celle de l'agent. Le système selon l'invention segmente l'enregistrement afin d'extraire différents mots, tel que des mots exprimant la colère. Ledit système peut également segmenter au moins une partie de la voix du client avant de créer un profil de tons, et il formate les mots segmentés et les profils de tons pour une transmission réseau à un serveur. Le serveur compare les mots et/ou les profils de tons du client avec de multiples mots et/ou profils de tons connus stockés dans une base de données, afin de déterminer d'éventuelles correspondances importantes. L'identification d'éventuelles correspondances peut servir à une pluralité d'objectifs, par exemple pour fournir une rétroaction représentative ou un suivi client.
One-to-many comparisons of callers' words and/or voice prints with known words and/or voice prints to identify any substantial matches between them. When a customer communicates with a particular entity, such as a customer service center, the system makes a recording of the real-time call including both the customer's and agent's voices. The system segments the recording to extract different words, such as words of anger. The system may also segment at least a portion of the customer's voice to create a tone profile, and it formats the segmented words and tone profiles for network transmission to a server. The server compares the customer's words and/or tone profiles with multiple known words and/or tone profiles stored on a database to determine any substantial matches. The identification of any matches may be used for a variety of purposes, such as providing representative feedback or customer follow-up.

Claims

Description

Topics

Download Full PDF Version (Non-Commercial Use)

Patent Citations (3)

    Publication numberPublication dateAssigneeTitle
    US-2002120519-A1August 29, 2002Martin Jeffrey W., Campbell HawkinsDistributed information methods and systems used to collect and correlate user information and preferences with products and services
    US-2004008828-A1January 15, 2004Scott Coles, Gentle Christopher R., Chris Goringe, Rodney Harrison, Orbach Julian J.Dynamic information retrieval system utilizing voice recognition
    US-5623539-AApril 22, 1997Lucent Technologies Inc.Using voice signal analysis to identify authorized users of a telephone system

NO-Patent Citations (0)

    Title

Cited By (8)

    Publication numberPublication dateAssigneeTitle
    US-8793131-B2July 29, 2014Verint Americas Inc.Systems, methods, and media for determining fraud patterns and creating fraud behavioral models
    US-8903859-B2December 02, 2014Verint Americas Inc.Systems, methods, and media for generating hierarchical fused risk scores
    US-8924285-B2December 30, 2014Verint Americas Inc.Building whitelists comprising voiceprints not associated with fraud and screening calls using a combination of a whitelist and blacklist
    US-8930261-B2January 06, 2015Verint Americas Inc.Method and system for generating a fraud risk score using telephony channel based audio and non-audio data
    US-9113001-B2August 18, 2015Verint Americas Inc.Systems, methods, and media for disambiguating call data to determine fraud
    US-9875739-B2January 23, 2018Verint Systems Ltd.Speaker separation in diarization
    US-9875742-B2January 23, 2018Verint Systems Ltd.Word-level blind diarization of recorded calls with arbitrary number of speakers
    US-9875743-B2January 23, 2018Verint Systems Ltd.Acoustic signature building for a speaker from multiple sessions