Canon Kabushiki Kaisha

Jebu Jacob Rajan

Jason Peter Andrew Charlesworth

Philip Neil Garner

Simon Michael Rowe

Michael James Taylor

A system is provided for allowing a user to add word models to a speech recognition system. In particular, the system allows a user to input a number of renditions of the new word and which generates from these a sequence of phonemes representative of the new word. This representative sequence of phonemes is stored in a word to phoneme dictionary together with the typed version of the word for subsequent use by the speech recognition system.

Speech processing system

A data structure is provided for annotating data files within a database. The annotation data comprises a phoneme and word lattice which allows the quick and efficient searching of data files within the database in response to a user's input query. The structure of the annotation data is such that it allows the input query to be made by voice and can be used for annotating various kinds of data files, such as audio data files, video data files, multimedia data files etc. The annotation data may be generated from the data files themselves or may be input by the user either from a voiced input or from a typed input.

Database searching and retrieval using phoneme and word lattice

A signal processing system is provided which receives signals from a number of different sensors which are representative of signals generated from a plurality of sources. The sensed signals are processed to determine the relative position of each of the sources relative to the sensors. This information is then used to separate the signals from each of the sources. The system can be used, for example, to separate the speech signal generated from a number of users in a meeting.

Signal processing system

Image data from cameras showing movement of a number of people, and sound data, is archived and processed to determine the position and orientation of each person's head and to determine at whom each person is looking. The speaker is determined by determining at which person most people are looking. Alternatively, the sound data is processed to determine the direction from which the sound came, and it is determined who is speaking by determining which person's head is in a position corresponding to the direction from which the sound came. The personal speech recognition parameters for the speaker are selected and used to convert the sound data to text data. Image data to be archived is chosen by selecting the camera which best shows the speaker and the participant to whom he is speaking. Data is stored in a meeting archive database.

Processing apparatus for determining which person in a group is speaking

A system is provided for detecting the presence of speech within an input audio signal. The system includes a memory for storing a predetermined function which gives, for a given set of audio signal values, a probability density for parameters of a predetermined speech model which is assumed to have generated the set of audio signal values, the probability density defining, for a given set of model parameter values, the probability that the predetermined speech model has those parameter values given that the speech model is assumed to have generated the set of audio signal values. The system applies a current set of received signal values to the stored probability density function and then draws samples from it using a Gibbs sampler. The system then analyses the samples to determine a set parameter values representative of the audio signal. The system then uses these parameter values to determine whether or not speech is present within the audio signals.

A speech processing system is provided which is operable to receive sets of signal values representative of a speech signal generated by a speech source as distorted by a transmission channel between the speech source and the speech processing system. The system stores data defining a predetermined function derived from a signal model which models both the speech source and the channel and defining a probability density function which gives, for a given set of model parameters, the probability that the signal model has those model parameters given that the signal model is assumed to have generated the received set of signal values. The system applies a current set of received signal values to the stored probability density function and then draws samples from it using a Gibbs sampler. The system then analyses the samples to determine a set of parameter values representative of the speech signal before it was distorted by the channel.

A speech processing system is provided which is operable to receive sets of signal values representative of a speech signal generated by a speech source. The system is operable to determine a measure of the quality of the speech signal by performing a statistical analysis of the received sets of signal values. The system stores data defining a predetermined function derived from a signal model which models the speech source and which defines a probability density function which gives, for a given set of model parameters, the probability that the signal model has those model parameters given that the signal model is assumed to have generated the received set of signal values. The system applies a current set of received signal values to the stored probability density function and then draws samples from it using a Gibbs sampler. The system then analyses the samples to determine a measure of the variance of some of the samples and then outputs a signal indicative of the quality of the received speech signal values in dependence upon the determined variance.

The data structure is used in accessing a plurality of data files. The data stucture comprises a plurality of annotation storage areas adapted to correspond with the data files, each annotation storage area containing an annotation an annotation representing a time sequential signal and each annotation storage area comprising a plurality of block storage areas each containing phoneme and word data forming a respective temporal block of the annotation and each block having an associated time index identifying a timing of the block within the corresponding annotation. Each block storage area includes a plurality of node storage areas, each asociated with a node which represents a point in time at which a word and/or phoneme begins or ends within the corresponding annotation, and each node storage area having a time offset storage area containing a time offset defining the point in time represented by the node relative to the time index associated with the corresponding block. Each node storage area further has one or more phoneme link storage areas, each having a phoneme storage area containing data identifying a phoneme associated with corresponding node; or one or more word link storage areas, each having a word storage area containing data identifying a word associated with the corresponding node. One or more of the node storage areas has at least one of the phoneme link storage areas and at least one of the word link storage areas.

Database annotation and retrieval including phoneme data

A signal processing system is provided which includes one or more receivers for receiving signals generated by a plurality of signal sources. The system has a memory for storing a predetermined function which gives, for a set of input signal values, a probability density for parameters of a respective signal model which is assumed to have generated the signals in the received signal values. The system applies a set of received signal values to the stored function to generate the probability density function and then draws samples from it. The system then analyses the drawn samples to determine parameter values representative of the signal from at least one of the sources.

Growing community of inventors

Bracknell, United Kingdom

Jebu Jacob Rajan