Abstract: A mechanism for local language numeral conversion in dynamic numeric computing is disclosed. A method of embodiments of the invention includes receiving a string array of numeric data in a local language, wherein the numeric data used in dynamic calculations performed by the application, converting characters of the string array of numeric data from local language characters to corresponding English digits in an American Standard Code for Information Interchange (ASCII) format by utilizing a number conversion matrix, and providing the English digits in the ASCII format to a processing function of the application for use with the dynamic calculations of the application.

Abstract: Streaming voice signals, such as might be received at a contact center or similar operation, are analyzed to detect the occurrence of one or more unprompted, predetermined utterances. The predetermined utterances preferably constitute a vocabulary of words and/or phrases having particular meaning within the context in which they are uttered. Detection of one or more of the predetermined utterances during a call causes a determination of response-determinative significance of the detected utterance(s). Based on the response-determinative significance of the detected utterance(s), a responsive action may be further determined. Additionally, long term storage of the call corresponding to the detected utterance may also be initiated. Conversely, calls in which no predetermined utterances are detected may be deleted from short term storage.

Abstract: Aspects of the subject matter described herein relate to language translation. In aspects, a reference to a language translation component is embedded or otherwise inserted into a Web page. When the Web page is rendered, code corresponding to the language translation component may be downloaded and executed. Once executed, the translation component may access other content in the Web page and allow a user to request translation of the Web page. Upon receiving an indication that translation is desired, the translation component may send content in the Web page to a translation service and receive translated content. The translation component may then provide this translated content to a user viewing the Web page.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for collecting web data in order to create diverse language models. A system configured to practice the method first crawls, such as via a crawler operating on a computing device, a set of documents in a network of interconnected devices according to a visitation policy, wherein the visitation policy is configured to focus on novelty regions for a current language model built from previous crawling cycles by crawling documents whose vocabulary considered likely to fill gaps in the current language model. A language model from a previous cycle can be used to guide the creation of a language model in the following cycle. The novelty regions can include documents with high perplexity values over the current language model.

Abstract: Embodiments of the present invention provide an approach for estimating the accuracy of a transcription of a voice recording. Specifically, in a typical embodiment, each word of a transcription of a voice recording is checked against a customer-specific dictionary and/or a common language dictionary. The number of words not found in either dictionary is determined. An accuracy number for the transcription is calculated from the number of said words not found and the total number of words in the transcription.

Abstract: Embodiments are disclosed that relate to identifying phonetically similar speech grammar terms during computer program development. For example, one disclosed embodiment provides a method including providing a speech grammar development tool configured to receive input of a text representation of each of a plurality of proposed speech grammar terms, convert each text representation to a phonetic representation of the speech grammar term, compare the phonetic representation of the speech grammar term to the phonetic representations of other speech grammar terms using a weighted similarity matrix, and provide an output regarding risk of confusion between two proposed speech grammar terms based upon a comparison of the phonetic representations of the two proposed speech grammar terms. The method further includes receiving data regarding incorrect speech grammar term identification, and modifying one or more weights in the weighted similarity matrix based upon the data.

Abstract: In one embodiment, a method for detecting autism in a natural language environment using a microphone, sound recorder, and a computer programmed with software for the specialized purpose of processing recordings captured by the microphone and sound recorder combination, the computer programmed to execute the method, includes segmenting an audio signal captured by the microphone and sound recorder combination using the computer programmed for the specialized purpose into a plurality recording segments. The method further includes determining which of the plurality of recording segments correspond to a key child. The method further includes determining which of the plurality of recording segments that correspond to the key child are classified as key child recordings.

Abstract: Methods, apparatus, and products are disclosed for record disambiguation in a multimodal application operating on a multimodal device, the multimodal device supporting multiple modes of interaction including at least a voice mode and a visual mode, that include: prompting, by the multimodal application, a user to identify a particular record among a plurality of records; receiving, by the multimodal application in response to the prompt, a voice utterance from the user; determining, by the multimodal application, that the voice utterance ambiguously identifies more than one of the plurality of records; generating, by the multimodal application, a user interaction to disambiguate the records ambiguously identified by the voice utterance in dependence upon record attributes of the records ambiguously identified by the voice utterance; and selecting, by the multimodal application for further processing, one of the records ambiguously identified by the voice utterance in dependence upon the user interaction.

Abstract: A method and apparatus for speech translation. The method includes: receiving a source speech; extracting non-text information in the source speech; translating the source speech into a target speech; and adjusting the translated target speech according to the extracted non-text information so that the target speech preserves the non-text information in the source speech. The apparatus includes: a receiving module for receiving source speech; an extracting module for extracting non-text information in the source speech; a translation module for translating the source speech into a target speech; and an adjusting module for adjusting the translated target speech according to the extracted non-text information so that the target speech preserves the non-text information in the source speech.

Abstract: A method and system for enhancing dialog determined by an audio input signal. In some embodiments the input signal is a stereo signal, and the system includes an analysis subsystem configured to analyze the stereo signal to generate filter control values, and a filtering subsystem including upmixing circuitry configured to upmix the input signal to generate a speech channel and non-speech channels and a peaking filter configured to filter the speech channel to enhance dialog while being steered by at least one of the control values. The filtering subsystem also includes ducking circuitry for attenuating the non-speech channels while being steered by at least some of the control values, and downmixing circuitry configured to combine outputs of the peaking filter and ducking circuitry to generate a filtered stereo output.

Abstract: A method, apparatus and system may enhance translation results from translation applications running on mobile devices. Specifically, according to one embodiment, location data may be automatically identified by a location awareness or location detection scheme (e.g., Global Positioning System or GPS, WiFi and/or 3G) on the device or coupled to the device. The location data may be utilized by the enhanced translation scheme according to an embodiment of the invention to pin point the specific physical geographical location of the device. Thereafter, if an enhanced local language dictionary exists that includes any local dialect details, the enhanced local language dictionary may be downloaded to the device. When the user desires to translate a word and/or phrase, the device may look up the meaning in the downloaded enhanced local language dictionary, thus ensuring that the translation is specific to that geographic location.

Abstract: Embodiments of the present invention provide an approach for estimating the accuracy of a transcription of a voice recording. Specifically, in a typical embodiment, each word of a transcription of a voice recording is checked against a customer-specific dictionary and/or a common language dictionary. The number of words not found in either dictionary is determined. An accuracy number for the transcription is calculated from the number of said words not found and the total number of words in the transcription.

Abstract: Architecture that detects and corrects writing errors in a human language based on the utilization of three different stages: error detection, correction candidate generation, and correction candidate ranking. The architecture is a generic framework for generating fluent alternatives to non-grammatical word sequences in a written sample. Error detection is addressed by a suite of language model related scores and other scores such as parse scores that can identify a particularly unlikely sequence of words. Correction candidate generation is addressed by a lookup in a very large corpus of “correct” English that looks for alternative arrangements of the same or similar words or subsequences of these words in the same context. Correction candidate ranking is addressed by a language model ranker.

Abstract: A computing device can capture video data of at least a portion of a mouth area (e.g., mouth, lips, tongue, chin, jaw) of a user of the device. The computing device can also capture sound data including a voice of the user as well as noise (e.g. background noise). The video data can be processed to detect a movement of the portion of the mouth area. The movement of the portion of the mouth area can be analyzed and compared with mouth area movement models characteristic of oral communication (e.g., speech, song). If the movement of the portion of the mouth area corresponds to at least one model characteristic of oral communication, then the movement indicates that the user is likely engaging in oral communication. Noise reduction can be applied and/or increased on the captured sound data to reduce noise and in turn enhance the user's voice.

Abstract: A dialog manager and spoken dialog service having a dialog manager generated according to a method comprising selecting a top level flow controller based on application type, selecting available reusable subdialogs for each application part, developing a subdialog for each application part not having an available subdialog and testing and deploying the spoken dialog service using the selected top level flow controller, selected reusable subdialogs and developed subdialogs. The dialog manager capable of handling context shifts in a spoken dialog with a user. Application dependencies are established in the top level flow controller thus enabling the subdialogs to be reusable and to be capable of managing context shifts and mixed initiative dialogs.

Abstract: Provided is a process for extracting conveyance records from unstructured text documents, the process including: obtaining, with one or more processors, a plurality of documents describing, in unstructured form, one or more conveyances of interest in real property; determining, with one or more processors, for each of the documents, a respective jurisdiction; selecting, with one or more processors, from a plurality of language processing models for the English language, a respective language processing model for each of the documents based on the respective determined jurisdiction; extracting, with one or more processors, for each of the documents, a plurality of structured conveyance records from each of the plurality of documents by applying the language processing model selected for the respective document based on the jurisdiction associated with the document; and storing, with one or more processors, the extracted, structured conveyance record in memory.

Abstract: A method, a computer program product, and an apparatus for managing a voice communication are provided. In one illustrative embodiment, an audio phrase produced by a first user is identified in the voice communication between the first user and a second user. A determination is made whether the audio phrase is present in a policy which prohibits the transmission of the set of undesired audio phrases. Responsive to a determination that the audio phrase is present in the policy which prohibits the transmission of the set of undesired audio phrases, a communication of the audio phrase is modified.

Abstract: In one embodiment, the system and method for expressive language development; a method for detecting autism in a natural language environment using a microphone, sound recorder, and a computer programmed with software for the specialized purpose of processing recordings captured by the microphone and sound recorder combination; and the computer programmed to execute a method that includes segmenting an audio signal captured by the microphone and sound recorder combination using the computer programmed for the specialized purpose into a plurality recording segments. The method further includes determining which of the plurality of recording segments correspond to a key child. The method also includes extracting acoustic parameters of the key child recordings and comparing the acoustic parameters of the key child recordings to known acoustic parameters for children. The method returns a determination of a likelihood of autism.

Abstract: A voice signal is synthesized using a plurality of phonetic piece data each indicating a phonetic piece containing at least two phoneme sections corresponding to different phonemes. In the apparatus, a phonetic piece adjustor forms a target section from first and second phonetic pieces so as to connect the first and second phonetic pieces to each other such that the target section includes a rear phoneme section of the first piece and a front phoneme section of the second piece, and expands the target section by a target time length to form an adjustment section such that a central part is expanded at an expansion rate higher than that of front and rear parts of the target section, to thereby create synthesized phonetic piece data having the target time length. A voice synthesizer creates a voice signal from the synthesized phonetic piece data.

Abstract: A method for automatically providing a hypothesis of a linguistic formulation that is uttered by users of a voice service based on an automatic speech recognition system and that is outside a recognition domain of the automatic speech recognition system. The method includes providing a constrained and an unconstrained speech recognition from an input speech signal, identifying a part of the constrained speech recognition outside the recognition domain, identifying a part of the unconstrained speech recognition corresponding to the identified part of the constrained speech recognition, and providing the linguistic formulation hypothesis based on the identified part of the unconstrained speech recognition.