Conexant Systems, Inc.

Mindspeed Technologies, Inc.

Wiav Solutions LLC

Ayman O Asadi

Khaled Assaleh

Sahar E Bou-Ghazale

According to a disclosed embodiment, an endpointer determines the background energy of a first portion of a speech signal, and a cepstral computing module extracts one or more features of the first portion. The endpointer calculates an average distance of the first portion based on the features. Subsequently, an energy computing module measures the energy of a second portion of the speech signal, and the cepstral computing module extracts one or more features of the second portion. Based on the features of the second portion, the endpointer calculates a distance of the second portion. Thereafter, the endpointer contrasts the energy of the second portion with the background energy of the first portion, and compares the distance of the second portion with the distance of the first portion. The second portion of the speech signal is classified by the endpointer as speech or non-speech based on the contrast and the comparison.

System and method for an endpoint detection of speech for improved speech recognition in noisy environments

System and method for a endpoint detection of speech for improved speech recognition in noisy environments

A low complexity speaker verification system that employs universal cohort models an automatic score thresholding. The universal cohort models are generated using a simplified cohort model generating scheme. In certain embodiments of the invention, a simplified hidden Markov modeling (HMM) scheme is used to generate the cohort models. In addition, the low complexity speaker verification system is trained by various users of the low complexity speaker verification system. The total number of users of the low complexity speaker verification system may be modified over time as required by the specific application, and the universal cohort models may be updated accordingly to accommodate the new users. The present invention employs a combination of universal cohort modeling and thresholding to ensure high performance. In addition, given the simplified generation of the cohort models and training of the low complexity speaker verification system, substantially reduced processing resources and memory are amenable for high performance of the low complexity speaker verification system. In certain embodiments of the invention, the invention is an integrated speaker training and speaker verification system that performs both training and speaker verification.

Growing community of inventors

Laguna Niguel, CA, United States of America

Ayman O Asadi