Abstract: A computer-implemented technique for transcribing audio data includes generating, along a vertical axis on a display of a client device, an image representing audio content. The technique further includes receiving, from a user of the client device, a selection of a portion of the image; and generating, via an audio module of the client device, an audio output corresponding to the selected portion of the image. The technique further includes receiving, from the user, a selection indicating a position along the vertical axis on the display to enter a text portion representing the audio output, wherein the position is aligned to the selected portion of the image. The technique further includes receiving, from the user, the text portion representing the audio output; and displaying, on the display, the text portion at the position, wherein the text portion extends along a horizontal axis on the display.

Abstract: Automatic text skimming using lexical chains may be provided. First, at least one lexical chain may be created from an electronic document. Next, a list of positions within the electronic document may be created. The positions may include where at least one concept represented by one of the at least one lexical chain is mentioned. In addition, a list of the position where the at least one concept is mentioned may be assembled. A selection of at least one concept may be received from the list.

Abstract: Disclosed is a system and method for implementing compression coding of audio signals, such as speech signals, using two long-term prediction (LTP) models. The method determines the parameters of a second long-term prediction model on the basis of the parameters of at least one first LTP model. The present invention is aimed at switching from an LTP model with a single coefficient (monotap) to an LTP model with several coefficients, (multitap) and vice versa, as well as at switching between two multitap LTP models. The complexity of the method may be adjusted, especially as a function of a desired compromise between a target complexity and a desired quality. A device for implementing the method according to the invention is, moreover, very useful for multiple codings in cascade (transcodings) or in parallel (multi-codings and multi-mode codings).

Abstract: In a selective signal encoder, an input signal is first encoded using a core layer encoder to produce a core layer encoded signal. The core layer encoded signal is decoded to produce a reconstructed signal and an error signal is generated as the difference between the reconstructed signal and the input signal. The reconstructed signal is compared to the input signal. One of two or more enhancement layer encoders selected dependent upon the comparison and used to encode the error signal. The core layer encoded signal, the enhancement layer encoded signal and the selection indicator are output to the channel (for transmission or storage, for example).

Abstract: The present invention proposes a new method for improving the performance of a real-valued filterbank based spectral envelope adjuster. By adaptively locking the gain values for adjacent channels dependent on the sign of the channels, as defined in the application, reduced aliasing is achieved. Furthermore, the grouping of the channels during gain-calculation, gives an improved energy estimate of the real valued subband signals in the filterbank.

Abstract: A method for entering keys in a small key pad is provided. The method comprising the steps of: providing at least a part of keyboard having a plurality of keys; and predetermining a first probability of a user striking a key among the plurality of keys. The method further uses a dictionary of selected words associated with the key pad and/or a user.

Abstract: A continuous comfort noise is provided that is overlaid for the entire duration of a conference call scenario. The comfort noise may be adapted to match the levels of the actual background noise detected on one or more of the conference call participant's devices on the transmitting end(s) of a conference call as well as the participants' speech levels. The comfort noise may also be adapted to the type of listening device employed on the receiving end of a conference call. The comfort noise level may be customized to an appropriate and comfortable level for the type of listening device being used, and the system may continuously mix the comfort noise with incoming audio signals for the entire duration of a conference call, lowering the comfort noise level gradually during speaking periods for additional user experience improvement.

Abstract: The present invention discloses a method and an apparatus for extracting a prosodic feature of a speech signal, the method including: dividing the speech signal into speech frames; transforming the speech frames from time domain to frequency domain; and extracting respective prosodic features for different frequency ranges. According to the above technical solution of the present invention, it is possible to effectively extract the prosodic feature which can combine with a traditional acoustics feature without any obstacle.

Abstract: Discrimination between two classes comprises receiving a set of frames including an input signal and determining at least two different feature vectors for each of the frames. Discrimination between two classes further comprises classifying the two different feature vectors using sets of preclassifiers trained for at least two classes of events and from that classification, and determining values for at least one weighting factor. Discrimination between two classes still further comprises calculating a combined feature vector for each of the received frames by applying the weighting factor to the feature vectors and classifying the combined feature vector for each of the frames by using a set of classifiers trained for at least two classes of events.

Abstract: A system for managing recognition errors in a multiple dialog state environment incorporates an error management module. The error management module includes error counters and error set points associated with the system globally as well as associated with specific dialog states. User interaction within the system may then be managed based upon the status of the error counters in relation to the error set points.

Abstract: Speech enabled media sharing in a multimodal application including parsing, by a multimodal browser, one or more markup documents of a multimodal application; identifying, by the multimodal browser, in the one or more markup documents a web resource for display in the multimodal browser; loading, by the multimodal browser, a web resource sharing grammar that includes keywords for modes of resource sharing and keywords for targets for receipt of web resources; receiving, by the multimodal browser, an utterance matching a keyword for the web resource, a keyword for a mode of resource sharing and a keyword for a target for receipt of the web resource in the web resource sharing grammar thereby identifying the web resource, a mode of resource sharing, and a target for receipt of the web resource; and sending, by the multimodal browser, the web resource to the identified target for the web resource using the identified mode of resource sharing.

Abstract: Systems and methods are described that facilitate phrase-based statistical machine translation (SMT) incorporating bigram (or higher n-gram) language models by modeling bi-phrases as nodes in a graph. Additionally, construction of a translation is modeled as a “tour” amongst the nodes of the graph, such that a translation solution is generated by treating the graph as a generalized traveling salesman problem (GTSP) and solving for an optimal tour. The overall cost of a tour is computed by adding the costs associated with the edges traversed during the tour. Thus, the described systems and methods map the SMT problem directly into a GTSP problem, which itself can be directly converted into a TSP problem.

Abstract: The present invention proposes a new method for improving the performance of a real-valued filterbank based spectral envelope adjuster. By adaptively locking the gain values for adjacent channels dependent on the sign of the channels, as defined in the application, reduced aliasing is achieved. Furthermore, the grouping of the channels during gain-calculation, gives an improved energy estimate of the real valued subband signals in the filterbank.

Abstract: DEAF-core technology converts inputs to outputs accessible to people with disabilities. Communication is improved with DEAF-core technology by using data storage and transmission format that includes both semantic information and content. User-defined input, responsible for conveying semantic information, and raw analog input, such as text, are converted into a unique XML format (“gh XML”). “gh XML” includes standard XML encoded with accessibility information that allows a user to communicate both verbal (text) and non-verbal (semantic) information as part of the input. “gh XML” is a temporary format which is further converted using XSLT (extensible Stylesheet Language Transformations) into individual versions of XML specific to each output. After the “gh XML” is converted into the desired XML format, custom rendering engines specific to the desired output convert the individual version of XML into a viable analog format for display.

Abstract: A method for detecting data in a sequence of characters or text using both a statistical engine and a pattern engine. The statistical engine is trained to recognize certain types of data and the pattern engine is programmed to recognize the grammatical pattern of certain types of data. The statistical engine may scan the sequence of characters to output first data, and the pattern engine may break down the first data into subsets of data. Alternatively, the statistical engine may output items that have a predetermined probability or greater of being a certain type of data and the pattern engine may then detect the data from the output items and/or remove incorrect information from the output items.

Abstract: Provided are parametric audio encoding and decoding apparatuses and methods thereof. In the parametric audio encoding method, an audio signal is segmented into a plurality of segments. At least one sine wave is extracted from each of the segments, and the extracted sine waves are connected. It is determined whether an extracted sine wave is a birth sine wave. If the extracted sine wave is a birth sine wave, a bit stream is generated by encoding the phase of the birth sine wave on the basis of the frequency of the birth sine wave, wherein the number of bits allocated to encode the phase of the birth sine wave is adjusted according to the frequency of the birth sine wave.

Abstract: An information processing system includes an information processing unit, an information changing unit, and an information reproducing unit. The information processing unit processes the information received by a sensor and transmits the result of processing to the information reproducing unit. The information changing unit adds or deletes information to or from the result of processing, obtained by the information processing unit, by using an information analysis unit and a change-processing unit. If the information processing is interpretation that includes voice recognition, translation and voice synthesis, the first language received by the sensor is translated into the second language by the information processing unit and is reproduced by the information reproducing unit.

Abstract: A device extracts prosodic information including a power value from a speech data and an utterance section including a period with a power value equal to or larger than a threshold, from the speech data, divides the utterance section into each section in which a power value equal to or larger than another threshold, acquires phoneme sequence data for each divided speech data by phoneme recognition, generates clusters which is a set of the classified phoneme sequence data by clustering, calculates an evaluation value for each cluster, selects clusters for which the evaluation value is equal to or larger than a given value as candidate clusters, determines one of the phoneme sequence data from the phoneme sequence data constituting the cluster for each candidate cluster to be a representative phoneme sequence, and selects the divided speech data corresponding to the representative phoneme sequence as listening target speech data.

Abstract: An audio encoder for providing an output signal using an input audio signal includes a patch generator, a comparator and an output interface. The patch generator generates at least one bandwidth extension high-frequency signal, wherein a bandwidth extension high-frequency signal includes a high-frequency band. The high-frequency band of the bandwidth extension high-frequency signal is based on a low frequency band of the input audio signal. A comparator calculates a plurality of comparison parameters. A comparison parameter is calculated based on a comparison of the input audio signal and a generated bandwidth extension high-frequency signal. Each comparison parameter of the plurality of comparison parameters is calculated based on a different offset frequency between the input audio signal and a generated bandwidth extension high-frequency signal.

Abstract: An apparatus for generating a synthesis audio signal using a patching control signal has a first converter, a spectral domain patch generator, a high frequency reconstruction manipulator and a combiner. The first converter is configured for converting a time portion of an audio signal into a spectral representation. The spectral domain patch generator is configured for performing a plurality of different spectral domain patching algorithms, wherein each patching algorithm generates a modified spectral representation having spectral components in an upper frequency band derived from corresponding spectral components in a core frequency band of the audio signal.