Abstract: A method of mitigating errors in a distributed speech recognition process. The method comprises the steps of identifying a group comprising one or more vectors which have undergone a transmission error, and replacing one or more speech recognition parameters in the identified group of vectors. In one embodiment all the speech recognition parameters of each vector of the group are replaced by replacing the whole vectors, and each respective replaced whole vector is replaced by a copy of whichever of the preceding or following vector without error is closest in receipt order to the vector being replaced.

Abstract: A method and apparatus for distributed speech recognition serve to mitigate the effect of transmission errors. The method comprises the steps of identifying speech recognition parameters which have been subjected to a transmission error, and processing data to be sent to the speech recognition decoder to ensure that any speech recognition parameters which have been subjected to such an error are excluded from back-end processing. The speech recognition parameters which have been subjected to transmission errors are excluded from back-end processing by replacing those parameters with data which is selected so as to be rejected by the speech recognition decoder as abnormal and/or non-speechlike.

Abstract: A voice communications device (4) and speech processing method are described. A speech signal, generated by a microphone (41) in response to speech input (2) in to the microphone (41) by a user (1), has a proportion extracted therefrom. The speech signal is transmitted to an appliction apparatus that may be integral or remote. A speech quality value is evaluated for the extracted speech signal. An indication of the quality of the speech signal, based on the speech quality value, is indicated to the user. Thus a direct indication of the current quality of a received speech signal, in a form that is easily interpreted by a non-expert user of the device, is provided, thereby providing the use with an opportunity to improve the sppech quality. Examples of appliction apparatus include hands-free telephones and automatic speech recognition systems.

Abstract: A method of processing a speech signal in noise, comprising: determining a frequency spectrum of a frame of the speech signal; determining a value of the pitch of the frame of the speech signal; identifying peakes (12, 14, 16, 22, 28, 32) in the spectrum; and evaluating the peaks individually to determine respective scores for the peaks, the score for a peak being a measure of the likelihood that the peak is a harmonic band of teh speech signal. As a consequence there is: (a) no need for high f0 accuracy as there is no need to predict long sequences of harmonic positions; and (b) no need for an assumption of harmonic integrity at all points.

Abstract: A method of processing received data in a distributed speech recognition process. The method comprises the steps of comparing a received form of the common header information from each of a plurality of header frames; classifying a predetermined number of the same received form as a reference; and processing one or more received data frames whose received common header information is different to the reference by using the reference form instead of the received different form. Also described is an apparatus for processing received data in a distributed speech recognition process.

Abstract: A method and apparatus for distributed speech recognition serve to mitigate the effect of transmission errors. The method comprises the steps of identifying speech recognition parameters which have been subjected to a transmission error, and processing data to be sent to the speech recognition decoder to ensure that any speech recognition parameters which have been subjected to such an error are excluded from back-end processing. The speech recognition parameters which have been subjected to transmission errors are excluded from back-end processing by replacing those parameters with data which is selected so as to be rejected by the speech recognition decoder as abnormal and/or non-speechlike.