Cirrus Logic International Semiconductor Limited

Agnitio Sl

Carlos Vaquero Aviles-Casco

Marta Garcia Gomar

Luis Buera Rodriguez

Luiz Buera Rodriguez

Antonio Miguel Artiaga

A tamper-resistant element for use in speaker recognition, the tamper-resistant element being adapted for storing data representing speaker information based on speaker recognition enrollment data and for checking whether information based on a speaker recognition testing signal matches the speaker information, characterized in that the tamper-resistant element is also adapted for carrying out a data integrity check, a system comprising such a tamper-resistant element and method for speaker recognition.

Tamper-resistant element for use in speaker recognition

Method for text-dependent Speaker Recognition using a speaker adapted Universal Background Model, wherein the speaker adapted Universal Background Model is a speaker adapted Hidden Markov Model comprising channel correction.

Speaker recognition

A tamper-resistant element for use in speaker recognition, the tamper-resistant element being adapted for storing data representing speaker information based on speaker recognition enrollment data and for checking whether information based on a speaker recognition testing signal matches the speaker information. The tamper-resistant element is also adapted for carrying out a data integrity check. Also, a system including such a tamper-resistant element and method for speaker recognition.

Method for speaker identification includes detecting a target speaker's utterance locally; extracting features from the detected utterance locally, analyzing the extracted features in the local device to obtain information on the speaker identification and/or encoding the extracted features locally, transmitting the encoded extracted features to a remote server, decoding and analyzing the received extracted features by the server to obtain information on the speaker identification, and transmitting the information on the speaker identification from the server to the location where the speaker's utterance was detected. The method further includes detecting speech activity locally. Extracting features, encoding the extracted features, and/or transmitting the encoded extracted features to the server, are only performed if speech activity above some predetermined threshold is detected.

Growing community of inventors

Madrid, Spain

Carlos Vaquero Aviles-Casco