Abstract: Techniques are presented to determine user-interest sensitive condensations of a passage. One or more passages are selected and user interest information, condensation transformations and optional meaning distortion constraints are identified. The foci of user interest within the selected passages are determined based the similarity of the elements in the selected passages to elements in the user interest information. The condensation transformations are applied to the selected passages to preferentially retain user foci while eliding less salient information. The resultant condensate provides signals the user-interest sensitive meaning of the passage. Meaning distortions constraints are optionally applied in conjunction with the condensation transformations or in creating the condensation transformations to reduce the likelihood of distorting the meaning of the passage.

Abstract: A system and method for reviewing inputted voice instructions in a vehicle-based telematics control unit. The system includes a microphone, a speech recognition processor, and an output device. The microphone receives voice instructions from a user. Coupled to the microphone is the speech recognition processor that generates a voice signal by performing speech recognition processing of the received voice instructions. The output device outputs the generated voice signal to the user. The system also includes a user interface for allowing the user to approve the outputted voice signal, and a communication component for wirelessly sending the generated voice signal to a server over a wireless network upon approval by the user.

Abstract: A method for generating a language component vocabulary VC for a speech recognition system having a language vocabulary V of a plurality of word forms is disclosed. The method includes: partitioning the language vocabulary V into subsets of word forms based on frequencies of occurrence of the respective word forms; and in at least one of the subsets, splitting word forms having frequencies less than a threshold to thereby generate word form components. Also disclosed is a method for use in speech recognition including: splitting an acoustic vocabulary comprising baseforms into baseform components and storing the baseform components; and, performing sound to spelling mapping on the baseform components so as to generate a baseform components to word parts table for use in subsequent decoding of speech.

Abstract: An audio encoder and decoder use architectures and techniques that improve the efficiency of quantization (e.g., weighting) and inverse quantization (e.g., inverse weighting) in audio coding and decoding. The described strategies include various techniques and tools, which can be used in combination or independently. For example, an audio encoder quantizes audio data in multiple channels, applying multiple channel-specific quantizer step modifiers, which give the encoder more control over balancing reconstruction quality between channels. The encoder also applies multiple quantization matrices and varies the resolution of the quantization matrices, which allows the encoder to use more resolution if overall quality is good and use less resolution if overall quality is poor. Finally, the encoder compresses one or more quantization matrices using temporal prediction to reduce the bitrate associated with the quantization matrices. An audio decoder performs corresponding inverse processing and decoding.

Abstract: A technique for computing perceptual noise in an audio signal that is computationally efficient. In one example embodiment, the technique includes computing perceptual noise in an input audio signal. The steps involve pre-computing NER (noise-to-excitation ratio) values associated with critical bands within a frame by zeroing out associated spectral coefficient values before the quantization loop, and also assuming bands with lower spectral energy than the band under consideration are zeroed out during quantization. When a critical band is zeroed out during quantization, the associated NER values which have been pre-computed are used in computing an overall perceptual distortion of the frame.

Abstract: A system suited to self-troubleshooting includes a processor which identifies normalized forms of at least some of the words of a natural language user query input by a user. The user query may describe a problem experienced with a machine, such as a printer. The processor retrieves text strings which may comprise problem statements stored in memory. Each retrieved problem statement includes at least one word with a normalized form which is recognized by the processor as being equivalent to one of the identified normalized forms. Each of the retrieved problem statements may be associated with at least one solution sequence for addressing the problem with the machine. In the event that the stored problem statements in memory are not fully responsive, the processor provides one or more options for refinement of the user query based on tags associated with those words of the problem statements which are responsive.

Abstract: Presented herein are systems and methods for generating an adaptive noise codebook for use with electronic speech systems. The noise codebook includes a plurality of entries which may be updated based on environmental noise sounds. The speech system includes a speech codebook and the adaptive noise codebook. The system identifies speech sounds in an audio signal using the speech and noise codebooks.

Abstract: Channel normalization for automatic speech recognition is provided. Statistics are measured from an initial portion of a speech utterance. Feature normalization parameters are estimated based on the measured statistics and a statistically derived mapping relating measured statistics and feature normalization parameters. In some examples, the measured statistics comprise measures of an energy from the initial portion of the speech utterance. In some examples, measures of the energy comprise extreme values of the energy.

Abstract: An embodiment of the present invention describes a method and system for using related data from external systems employing incompatible character sets to affect a business process. For one embodiment, a first external system uses a first character set. A first data set is received from the first external system, the first data set using the first character set. A second external system uses a second character set. A second data set is received from the second external system, the second data set using the second character set. The first data set and the second data set are converted to use a third character set, the third character set a superset of the first character set and the second character set. The first data set and the second data set, as converted and integrated, are then used to effect one or more business processes. For one embodiment, the third character set is Unicode.

Abstract: The present invention relates to a system and method for integrating telecommunications and cable networks for the purpose of providing telephone services to a cable host device over a cable network. The methods include registering a cable host device to receive telephone services, downloading telephone service software to a cable host device, cable host device sign on to the telephone services, associating a telephone with a cable host device, temporarily registering a cable host device, and activating and deactivating telephone services for a cable host device. Also described are systems for connecting telephone and cable networks to enable telephone services to be provided by cable host devices.

Abstract: A method and apparatus for indexing one or more audio signals using a speech to text engine and a phoneme detection engine, and generating a combined lattice comprising a text part and a phoneme part. A word to be searched is searched for in the text part, and if not found, or is found with low certainty is divided into phonemes and searched for in the phoneme parts of the lattice.

Abstract: A method includes applying at least one tag to at least one data element stored in a database the tag having at least one associated rule, utilizing the at least one associated rule to generate at least one variant of the data element, and storing the at least one variant in the database.

Abstract: Techniques are provided to generate alternate phrases from a packed meaning representation. The semantics of input items in a packed meaning representation are matched against a lexicon to determine initial entries in a phrasal information structure. Context, syntax and semantic information describing each phrasal entry are added to the phrasal information structure. Linear or other implications are used to determine a set of unordered rewrite rules. The unordered rewrite rules associate semantic information with pseudofacts such that a complete set of choices from the set of disjunctions in the packed meaning representation is selected. Semantic information associated with the unordered rewrite rules identifies entries in the phrasal information structure to be updated with the pseudofact of the unordered rewrite rule.

Abstract: The present invention provides a system for identifying, extracting, clustering and analyzing sentiment-bearing text. In one embodiment, the invention implements a pipeline capable of accessing raw text and presenting it in a highly usable and intuitive way.

Abstract: Methods and systems are provided for remote tuning and debugging of an automatic speech recognition system. Trace files are generated on-site from input speech by efficient, lossless compression of MFCC data, which is merged with compressed pitch and voicing information and stored as trace files. The trace files are transferred to a remote site where human-intelligible speech is reconstructed and analyzed. Based on the analysis, parameters of the automatic speech recognition system are remotely adjusted.

Abstract: A method, computer readable medium and system are provided which collect new words for addition to a lexicon for an agglutinative language. Sentences in the agglutinative language are retrieved from documents, for example from web pages. New word candidate character strings are identified in the retrieved sentences. The identified new word candidate character strings are filtered using a combination of a plurality of statistical criteria to generate a new words list. Words from the new words list are added to the lexicon.

Abstract: The present invention provides a task selection assistance apparatus, and a task selection assistance method, which enable burdens on a user to be alleviated in selecting a task for solving a problem. A domain candidate determining portion 210 determines domain candidates to be presented to the user from among domains stored in a task model DB 102, and a domain candidate transmitting portion 201 transmits the domain candidates to a portable terminal 101. A user selected domain obtaining portion 203 obtains a domain, which has been selected by the user, from the portable terminal 101, and the task candidate determining portion 211 determines task candidates to be presented to the user from among tasks stored in the task model DB 102 based on the domain selected by the user.

Abstract: A method for modelling, i.a. analyzing and/or synthesizing, a windowed signal such as sound or speech signals, by computing the frequencies and complex amplitudes from the signal using a nonlinear least squares method is disclosed. The computations complexity is reduced by taking into account the bandlimited property of a window.

Abstract: The present disclosure presents a useful metric for assessing the relative difficulty which non-native speakers face in pronouncing a given utterance and a method and systems for using such a metric in the evaluation and assessment of the utterances of non-native speakers. In an embodiment, the metric may be based on both known sources of difficulty for language learners and a corpus-based measure of cross-language sound differences. The method may be applied to speakers who primarily speak a first language speaking utterances in any non-native second language.

Abstract: Voice recognition methods and systems are disclosed. A voice signal is obtained for an utterance of a speaker. A runtime pitch is determined from the voice signal for the utterance. The speaker is categorized based on the runtime pitch and one or more acoustic model parameters are adjusted based on a categorization of the speaker. The parameter adjustment may be performed at any instance of time during the recognition. A voice recognition analysis of the utterance is then performed based on the acoustic model.