Abstract: A classifier voice interface of a user terminal may receive a query, may parse the query to identify an attribute, and may process the query to select a first domain-specific voice interface of a plurality of domain-specific voice interfaces based on the attribute, wherein each of the domain-specific voice interfaces comprises specialized information to process queries of different types. The classifier voice interface may further instruct the first domain-specific voice interface to process the query.

Abstract: Input of dictated information in an information processing apparatus is controlled. Utterances of speech are detected and interpreted as words. Word by word confirmation of the interpreted words is detected, the confirmation being associated with an adjustable timeout period. The timeout period may be adjusted according to a number of different measures, including an average time needed for confirmation, an average success rate of dictation, by the pace of dictation as performed by a user, and by a user's history based on statistics from previously performed dictation procedures.

Abstract: A mobile communication apparatus capable of presenting themes, a telecommunication system comprising a such apparatus, and a corresponding method are disclosed. The apparatus comprises a processor arranged to generate an audio signal in response to a set theme. The audio signal comprises a speech signal, wherein speech of the speech signal have voice characteristics which depend on the theme. Alternatively, processor is arranged to set a theme in response to contact information stored in a contact information database of the appatatus and associated with actions performed by the apparatus.

Abstract: Methods and systems for providing a voice interface are disclosed. A classifier voice interface of a user terminal may receive a query, may parse the query to identify an attribute, and may process the query to select a first domain-specific voice interface of a plurality of domain-specific voice interface based on the attribute, wherein each of the domain-specific voice interface comprises specialized information to process queries of different types. The classifier voice interface may further instruct the first domain-specific voice interface to process the query.

Abstract: An apparatus for providing dynamic vocabulary prediction for setting up a speech recognition network of resource constrained portable devices may include a recognition network element. The recognition network element may be configured to determine a confidence measure for each candidate recognized word for a current word to be recognized. The recognition network element may also be configured to select a subset of candidate recognized words as selected candidate words based on the confidence measure of each one of the candidate recognized words, and determine a recognition network for a next word to be recognized, the recognition network including likely follower words for each of the selected candidate words, e.g. using language model and highly frequently used words.

Abstract: Input of dictated information in an information processing apparatus is controlled. Utterances of speech are detected and interpreted as words. Word by word confirmation of the interpreted words is detected, the confirmation being associated with an adjustable timeout period. The timeout period may be adjusted according to a number of different measures, including an average time needed for confirmation, an average success rate of dictation, by the pace of dictation as performed by a user, and by a user's history based on statistics from previously performed dictation procedures.

Abstract: Pattern recognition, wherein a sequence of feature vectors is formed from a digitized incoming signal, the feature vectors comprising feature vector components, and at least one feature vector is compared with templates of candidate patterns by computing a distortion measure. A control signal based on at least one time-dependent variable of the recognition process is formulated, and the distortion measure is computed using only a subset of the vector components of the feature vector, the subset being chosen in accordance with said control signal. This reduces the computational complexity of the computation, as the dimensionality of the vectors involved in the computation is effectively reduced. Although such a dimension reduction decreases the computational need, it has been found not to significantly impair the classification performance.

Abstract: A method for improving noise robustness in speech recognition, wherein a front-end is used for extracting speech feature from an input speech and for providing a plurality of scaled spectral coefficients. The histogram of the scaled spectral coefficients is normalized to the histogram of a training set using Gaussian approximations. The normalized spectral coefficients are then converted into a set of cepstrum coefficients by a decorrelation module and further subjected to ceptral domain feature-vector normalization.

Abstract: A mobile communication apparatus capable of presenting themes, a telecommunication system comprising a such apparatus, and a corresponding method are disclosed. The apparatus comprises a processor arranged to generate an audio signal in response to a set theme. The audio signal comprises a speech signal, wherein speech of the speech signal have voice characteristics which depend on the theme. Alternatively, processor is arranged to set a theme in response to contact information stored in a contact information database of the appatatus and associated with actions performed by the apparatus.

Abstract: Words in a sequence of words that is obtained from speech recognition of an input speech sequence are presented to a user, and at least one of the words in the sequence of words is replaced, in case it has been selected by a user for correction. Words with a low recognition confidence value are emphasized; alternative word candidates for the at least one selected word are ordered according to an ordering criterion; after replacing a word, an order of alternative word candidates for neighboring words in the sequence is updated; the replacement word is derived from a spoken representation of the at least one selected word by speech recognition with a limited vocabulary; and the word that replaces the at least one selected word is derived from a spoken and spelled representation of the at least one selected word.

Abstract: This invention relates to a framework for converting a source speech signal associated with a source voice into a target speech signal that is a representation of the source speech signal associated with a target voice. The source speech signal is encoded into samples of encoding parameters, wherein the encoding comprises the step of segmenting the source speech signal into segments based on characteristics of the source speech signal. The samples of the encoding parameters, or a converted representation of the samples of the encoding parameters are then decoded to obtain the target speech signal. Therein, in the encoding, the decoding or in a separate step, samples of parameters related to the source speech signal are converted into samples of parameters related to the target speech signal. Therein, at least one of the encoding and the converting depends on the segments of the source speech signal.

Abstract: A speech recognition feature extractor for extracting speech features from a speech signal, comprising: a time-to-frequency domain transformer (FFT) for generating spectral magnitude values in the frequency domain from the speech signal; a frequency domain filtering block (Mel) for generating a sub-band value relating to spectral magnitude values of a certain frequency sub-band; a compression block (LOG) for compressing said sub-band values; a transformation block (DCT) for obtaining a set of de-correlated features from the compressed sub-band values; and normalising block (CN) for normalising de-correlated features.

Abstract: A speech recognition feature extractor includes a time-to-frequency domain transformer for generating spectral values in the frequency domain from a speech signal; a partitioning means for generating a first set and an additional set of spectral values in the frequency domain; a first feature generator for generating a first group of speech features using the first set of spectral values; a additional feature generator for generating an additional group of speech features using the additional set of spectral values; the feature generators arranged to operate in parallel, an assembler for assembling an output set of speech features from at least one speech feature from the first group of speech features and at least one speech feature from the additional group of speech features, and an anti-aliasing and sampling rate reduction block, where the first and the additional set of spectral values comprise at least one common spectral value.

Abstract: Pattern recognition, wherein a sequence of feature vectors is formed from a digitized incoming signal, the feature vectors comprising feature vector components, and at least one feature vector is compared with templates of candidate patterns by computing a distortion measure.

Abstract: A method for improving noise robustness in speech recognition, wherein a front-end is used for extracting speech feature from an input speech and for providing a plurality of scaled spectral coefficients. The histogram of the scaled spectral coefficients is normalized to the histogram of a training set using Gaussian approximations. The normalized spectral coefficients are then converted into a set of cepstrum coefficients by a decorrelation module and further subjected to ceptral domain feature-vector normalization.

Abstract: Detector for recognizing the living character of a finger which is arranged in a fingerprint recognizing apparatus and the detector is in contact with a print area (2) of the living finger constituting a print forming element (1) and the apparatus comprises for the examination of the print area (2) a print detector (5) which has a print imaging surface (4) partially covered by the print area (2). The detector comprises an electrode system (3) made of an electrically conductive material and sensing the presence of the print forming element (1), and an electrical evaluation unit coupled through electrical contacts (10) to the electrode system (3), the unit senses the change in state in the electrode system (3) caused by the proximity of the print forming element (1). The electrode system (3) is arranged on a portion of the print detector (5) covered by the print area (2) and it is coupled to the print imaging surface (4).

Abstract: Optical imaging system between an object plane (2.2) of a total reflexion prism (2) and an image plane, mainly for a fingerprint reading apparatus, that comprises an optics (3) for imaging the object plane to the image plane, and an electronic image detector (4) in the image plane. The optics defines an optical axis (3.0) and input and output pupils, respectively. The total reflexion prism (2) is arranged in front of the input pupil of the optics (3). The prism has a first surface receiving light for illuminating the object plane through the interior of the prism and a further surface through which light reflected from the object plane passes towards the optics. The object plane closes an angle with the optical axis, which is preferably between 45.degree. and 65.degree. if the refraction index of the prism is between 1.5 and 1.85. The object plane (2.2) of the total reflexion prism (2) is offset relative to the optical axis (3.