Abstract: A method and an apparatus for effecting the method are proposed that allow to define a subset of video signals from a source set of video signals on the basis of meta data available for the source set of video signals. The meta data assign a generic term to a sub-section of the audio channel of the source set of video signals, a class description to one or more sub-units of the sub-section for classifying the origin of the respective sub-unit, a category allocation to a segment, which is formed by a string of one or more classified sub-units of a sub-section, and a rating value to the segment for rating the reliability of the category allocation of the segment. The method includes steps for selecting segments of a sub-section with a rating value above a defined threshold value, assigning a priority value to each category, and specifying a first subset of video signals by defining an arrangement of selected segments by an order based on the respective priority and rating values related to each segment.

Abstract: An audio data segmentation apparatus for segmenting of audio data comprises audio data input means for supplying audio data, audio data clipping means for dividing the audio data supplied by the audio data input means into audio clips of a predetermined length, class discrimination means for discriminating the audio clips supplied by the audio data clipping means into predetermined audio classes, the audio classes identifying a kind of audio data included in the respective audio clip and segmenting means for segmenting the audio data into audio meta patterns based on a sequence of audio classes of consecutive audio clips, each meta pattern being allocated to a predetermined type of contents of the audio data. It is difficult to achieve good results with known methods for segmentation of audio data into meta patterns since the rules for the allocation of the meta patterns are dissatisfying.

Abstract: The present invention discloses an apparatus for automatic extraction of important events in audio signals comprising: signal input means for supplying audio signals; audio signal fragmenting means for partitioning audio signals supplied by the signal input means into audio fragments of a predetermined length and for allocating a sequence of one or more audio fragments to a respective audio window; feature extracting means for analysing acoustic characteristics of the audio signals comprised in the audio fragments and for analysing acoustic characteristics of the audio signals comprised in the audio windows; and important event extraction means for extracting important events in audio signals supplied by the audio signal fragmenting means based on predetermined important event classifying rules depending on acoustic characteristics of the audio signals comprised in the audio fragments and on acoustic characteristics of the audio signals comprised in the audio windows, wherein each important event extracted by

Abstract: To avoid an over-adaptation of a current acoustic model (CAM) to certain and frequently occuring words for speech phrases during on-line speaker adaptation of speech recognizers it is suggested to count adaptation numbers (aj) for each of said speech phrases (SPj) as numbers of times in that a distinct speech phrase (SPj) has been used as a basis for adapting said current acoustic model (CAM) and further to make the strength of adaptation of the current acoustic model (CAM) on the basis of said distinct speech phrase (SPj) dependent on its specific adaptation number (aj) so as to decrease the influence of frequent speech phrases (SPj) in the received speech flow on the adaptation process.

Abstract: There is proposed a method that may be universally used for controlling a man-machine interface unit. A learning sample is used in order at least to derive and/or initialize a target action (t) to be carried out and to lead the user from an optional current status (ec) to an optional desired target status (et) as the final status (ef). This learning sample (l) is formed by a data triple made up by an initial status (ei) before an optional action (a) carried out by the user, a final status (ef) after the action taken place (a).

Abstract: To increase the accuracy and the flexibility of a method for recognizing speech which employs a keyword spotting process on the basis of a combination of a keyword model (KM) and a garbage model (GM) it is suggested to associate at least one variable penalty value (Ptrans, P1, . . . , P6) with a global penalty (Pglob) so as to increase the recognition of keywords (Kj).

Abstract: To prevent adaptation to misrecognized words in unsupervised or on-line automatic speech recognition systems confidence measures are used or the user reaction is interpreted to decide whether a recognized phoneme, several phonemes, a word, several words or a whole utterance should be used for adaptation of the speaker independent model set to a speaker adapted model set or not and, in case an adaptation is executed, how strong the adaptation with this recognized utterance or part of this recognized utterance should be performed. Furtheron, a verification of the speaker adaptation performance is proposed to secure that the recognition rate never decreases (significantly), but only increases or stays at the same level.

Abstract: The invention provides a method for processing speech comprising the steps of receiving a speech input (SI) of a speaker, generating speech parameters (SP) from said speech input (SI), determining parameters describing an absolute loudness (L) of said speech input (SI), and evaluating (EV) said speech input (SI) and/or said speech parameters (SP) using said parameters describing the absolute loudness (L). In particular, the step of evaluation (EV) comprises a step of emotion recognition and/or speaker identification. Further, a microphone array comprising a plurality of microphones is used for determining said parameters describing the absolute loudness. With a microphone array the distance of the speaker from the microphone array can be determined and the loudness can be normalized by the distance.

Abstract: To increase the robustness and/or the recognition rate of methods for recognizing speech it is proposed to include phone boundary verification measure features (PBF) in the process of obtaining and/or generating confidence measures (CM) for obtained recognition results (RR).

Abstract: There is proposed a method that may be universally used for controlling a man-machine interface unit. A learning sample is used in order at least to derive and/or initialize a target action (t) to be carried out and to lead the user from an optional current status (ec) to an optional desired target status (et) as the final status (ef). This learning sample (l) is formed by a data triple made up by an initial status (ei) before an optional action (a) carried out by the user, a final status (ef) after the action taken place, and the action taken place (a).

Abstract: According to the present invention network devices that can be controlled via a speech unit included in the network can send a device-document describing its functionality and its speech interface to said speech unit. The speech unit combines those documents to a general document that forms the basis to translate recognized user-commands into user-network-commands to control the connected network-devices. A device-document comprises at least the vocabulary and the commands associated therewith for the corresponding device. Furtheron, pronunciation, grammar for word sequences, rules for speech understanding and dialog can be contained in such documents as well as the same information for multiple languages or information for dynamic dialogs in speech understanding. It is possible that one device contains several documents and dynamically sends them to the speech unit in case they are needed.

Abstract: Home networks low-cost digital interfaces are introduced that integrate entertainment, communication and computing electronics into consumer multimedia. Normally, these are low-cost, easy to use systems, since they allow the user to remove or add any kind of network devices with the bus being active. To improve the user interface a speech unit (2) is proposed that enables all devices (11) connected to the bus system (31) to be controlled by a single speech recognition device. The properties of this device, e.g. the vocabulary can be dynamically and actively extended by the consumer devices (11) connected to the bus system (31). The proposed technology is independent from a specific bus standard, e.g. the IEEE 1394 standard, and is well-suited for all kinds of wired wireless home networks. The speech unit (2) receives data and messages from the device. The speech unit (2) recognizes speaker-dependent commands. A Speech synthesizer synthesizes messages.

Abstract: To reduce the error rate when classifying emotions from an acoustical speech input (SI) only, it is suggested to include a process of speaker identification to obtain certain speaker identification data (SID) on the basis of which the process of recognizing an emotional state is adapted and/or configured. In particular, speaker-specific feature extractors (FE) and/or emotion classifiers (EC) are selected based on said speaker identification data (SID).

Abstract: To increase the recognition rate and quality in a process of recognizing speech an approximative set of pronunciation rules (APR) for a current pronunciation (CP) of a current speaker is determined in a given pronunciation space (PS) and then applied to a current pronunciation lexicon (CL) so as to perform a speaker specific adaptation of said current lexicon (CL).

Abstract: To increase the accuracy and the flexibility of a method for recognizing speech which employs a keyword spotting process on the basis of a combination of a keyword model (KM) and a garbage model (GM) it is suggested to associate at least one variable penalty value (Ptrans, P1, . . . , P6) with a global penalty (Pglob) so as to increase the recognition of keywords (Kj).

Abstract: To increase the recognition rate in processes for recognizing speech of a given target language (TL) which is spoken by a speaker of a different source language (SL) as a mother language, it is suggested to use pronunciation variants for said target language (TL) which are derived from said source languge (SL) without using non-native speech in said target langugae (TL).

Abstract: A method for recognizing speech is suggested wherein a lexicon (SL, CL) or a pronuniciation dictionary used for the recognition process is modified during the process of recognition starting with a starting lexicon (SL) and including after given numbers of steps of recognition (12) recognition related information (RRI) with respect to at least one recognition result (13) already obtained and wherein the process of recognition is then continued based on a modified lexicon (ML) as said current lexicon (CL).

Abstract: To increase the performance rate of large vocabulary continuous speech recognition applications it is suggested to first give only a rough estimation on whether or not recognized utterance (U) is accepted or rejected in its entirety. In the case of an acceptance of the utterance (U) a thorough reanalysis is performed afterwards to extract the meaning, intention, contained key-phrases/keywords and the confidence of the contained key-phrases/keywords. Therefore, the computational burden is focussed on the important sections of the utterance (U), namely on the key-phrases/keywords.

Abstract: To avoid an over-adaptation of a current acoustic model (CAM) to certain and frequently occuring words for speech phrases during on-line speaker adaptation of speech recognizers it is suggested to count adaptation numbers (aj) for each of said speech phrases (SPj) as numbers of times in that a distinct speech phrase (SPj) has been used as a basis for adapting said current acoustic model (CAM) and further to make the strength of adaptation of the current acoustic model (CAM) on the basis of said distinct speech phrase (SPj) dependent on its specific adaptation number (aj) so as to decrease the influence of frequent speech phrases (SPj) in the received speech flow on the adaptation process.

Abstract: Home networks low-cost digital interfaces are introduced that integrate entertainment, communication and computing electronics into consumer multimedia. Normally, these are low-cost, easy to use systems, since they allow the user to remove or add any kind of network devices with the bus being active. To improve the user interface a speech unit (2) is proposed that enables all devices (11) connected to the bus system (31) to be controlled by a single speech recognition device. The properties of this device, e.g. the vocabulary can be dynamically and actively extended by the consumer devices (11) connected to the bus system (31). The proposed technology is independent from a specific bus standard, e.g. the IEEE 1394 standard, and is well-suited for all kinds of wired or wireless home networks.