Speaker recognition in a multi-speaker environment and...

G - Physics – 10 – L

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

G10L 17/00 (2006.01) G07F 7/10 (2006.01) H04M 3/487 (2006.01)

Patent

CA 2524226

One-to-many comparisons of callers' voice prints with known voice prints to identify any 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 at least a portion of the customer's voice to create a customer voice print, and it formats the segmented voice print for network transmission to a server. The server compares the customer's voice print with multiple known voice prints to determine any matches, meaning that the customer's voice print and one of the known voice prints are likely from the same person. The identification of any matches can be used for a variety of purposes, such as determining whether to authorize a transaction requested by the customer.

Selon cette invention, des comparaisons un pour N d'empreintes vocales d'appelants avec des empreintes vocales connues permettent d'identifier d'éventuelles correspondances entre ces empreintes vocales. Lorsqu'un client communique avec une entité particulière, telle qu'un centre de service à la clientèle, le système effectue un enregistrement de l'appel en temps réel comprenant à la fois la voix du client et la voix de l'agent. Le système segmente l'enregistrement afin d'extraire au moins une partie de la voix du client dans le but de créer une empreinte vocale du client, après quoi le système formate l'empreinte vocale segmentée en vue de l'envoyer par le réseau à un serveur. Le serveur compare l'empreinte vocale du client à de multiples empreintes vocales connues afin d'identifier d'éventuelles correspondances indiquant que l'empreinte vocale du client et qu'une des empreintes vocales connues appartiennent à la même personne. L'identification d'éventuelles correspondances peut servir à des fins multiples, notamment à déterminer s'il convient ou non d'autoriser une transaction demandée par le client.

LandOfFree

Say what you really think

Search LandOfFree.com for Canadian inventors and patents. Rate them and share your experience with other people.

Rating

Speaker recognition in a multi-speaker environment and... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speaker recognition in a multi-speaker environment and..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speaker recognition in a multi-speaker environment and... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFCA-PAI-O-1559994

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.