Abstract: A method of synchronizing an operation for processing, by an automatic speech recognition system of a device, a voice sequence uttered by a speaker and an action of the speaker intended to trigger the processing by the device. The processing operation is effected by the device from a given time preceding the action of the speaker. A time interval between the given time and the action of the speaker corresponds to a given interval.

Abstract: This invention relates to a distributed speech recognition method comprising at least one user terminal and at least one server which can communicate with each other by means of a telecommunication network. The inventive method comprises the following steps consisting in: at the user terminal, attempting to associate a saved form with the signal to be recognized and, independently of said step, transmitting a signal to the server, indicating the signal to be recognized; and, at the server, attempting to associate a saved form with the signal received.

Abstract: Method of synchronization between an operation for processing, by automatic speech recognition, a voice sequence (Sv) uttered by a speaker and an action of said speaker intended to trigger said processing. According to the invention, said processing operation is effected from a given time (t0) preceding said action of the speaker. Application to automatic speech recognition.

Abstract: A method for the distributed construction of a voice recognition model that is intended to be used by a device comprising a model base and a reference base in which the modeling elements are stored. The method includes the steps of obtaining the entity to be modeled, transmitting data representative of the entity over a communication link to a server, determining a set of modeling parameters indicating the modeling elements, transmitting the modeling parameters to the device, determining the voice recognition model of the entity to be modeled as a function of at least the modeling parameters received and at least one modeling element that is stored in the reference base and indicated in the transmitted parameters, and subsequently saving the voice recognition model in the model base.

Abstract: This invention relates to a distributed speech recognition method comprising at least one user terminal and at least one server which can communicate with each other by means of a telecommunication network. The inventive method comprises the following steps consisting in: at the user terminal, attempting to associate a saved form with the signal to be recognized and, independently of said step, transmitting a signal to the server, indicating the signal to be recognized; and, at the server, attempting to associate a saved form with the signal received.

Abstract: This invention relates to a distributed speech recognition system. The inventive system consists of: at least one user terminal comprising means for obtaining an audio signal to be recognized, parameter calculation means and control means which are used to select a signal to be transmitted; and a server comprising means for receiving the signal, parameter calculation means, recognition means and control means which are used to control the calculation means and the recognition means according to the signal received.

Abstract: A process and device for blind equalization of the effects of a transmission channel on a speech signal. The speech signal is transformed into cepstral vectors which are representative of the speech signal over a given horizon. A reference cepstrum consisting of a constant cepstrum signal representative of the long-term cepstrum of the speech signal is calculated for each cepstral vector. Each of the cepstral vectors is subjected to adaptive filtering by LMS on the basis of the reference cepstrum so as to generate a set of equalized cepstral vectors on the basis of the calculation of an error signal between the reference cepstrum and equalized cepstral vectors. The error signal is expressed as the difference between the reference cepstrum component of a given rank and the component of the same rank of the equalized cepstral vector.

Abstract: A process and a system for adaptive filtering of a digital telephone signal, in which the digital telephone signal is submitted to a frequency transformation and to a sub-band filtering in order to produce a plurality of sub-band signals. Each of the sub-band signals is submitted in turn to an adaptive filtering starting from a reference signal based on a long-term statistics regarding the telephone signal, equalization by blind deconvolution of the effects of the telephone transmission lines on the digital telephone signal thus being obtained.

Abstract: For equalizing a speech signal constituted by an observed sequence of successive input sound frames, which speech signal is liable to be affected by disturbances, the speech signal is modelled by means of a hidden Markov model and, at each instant t: equalization filters are constituted in association with the paths in the Markov sense at instant t; at least a plurality of the equalization filters are applied to the frames to obtain, at instant t, a plurality of filtered sound frame sequences and an utterance probability for each of the paths respectively associated with the equalization filters applied; the equalization filter corresponding to the most probable path in the Markov sense is selected; and the filtered frame supplied by the selected equalization filter is selected as the equalized frame.