Lucent Technologies Inc.

Olivier Siohan

Qi P Li

Chin-Hui Lee

Frank Kao-ping Soong

Arun Chandrasekaran Surendran

A method and apparatus for extracting speech features from a speech signal in which the linear frequency spectrum data, as generated, for example, by a conventional frequency transform, is first converted to logarithmic frequency spectrum data having frequency data distributed on a substantially logarithmic (rather than linear) frequency scale. Then, a plurality of digital auditory filters is applied to the resultant logarithmic frequency spectrum data, each of these filters having a substantially similar shape, but centered at different points on the logarithmic frequency scale. Because each of the filters have a similar shape, the feature extraction approach of the present invention advantageously can be easily modified or tuned by adjusting each of the filters in a coordinated manner, with the adjustment of only a handful of filter parameters.

Automatic speech recognition with psychoacoustically-based feature extraction, using easily-tunable single-shape filters along logarithmic-frequency axis

A speaker verification method and apparatus which advantageously minimizes the constraints on the customer and simplifies the system architecture by using a speaker dependent, rather than a speaker independent, background model, thereby obtaining many of the advantages of using a background model in a speaker verification process without many of the disadvantages thereof. In particular, no training data (e.g. speech) from anyone other than the customer is required, no speaker independent models need to be produced, no a priori knowledge of acoustic rules are required, and, no multi-lingual phone models, dictionaries, or letter-to-sound rules are needed. Nonetheless, in accordance with an illustrative embodiment of the present invention, the customer is free to select any password phrase in any language. Specifically, and in accordance with an illustrative embodiment of the present invention, the background model comprises a hidden Markov model having a cruder acoustic resolution than the customer model, which may, for example, be achieved by providing a background model containing fewer states than the customer model.

Growing community of inventors

New Providence, NJ, United States of America

Olivier Siohan