Abstract: A sequential series of methods for optimized searching within a text (or alphanumeric string) database to retrieve specific and relevant results, followed by optimized restructuring and parsing of text data (or alphanumeric string), followed by creation/application of a natural language processing engine, followed by the creation/application of an automated analyzer is presented.

Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.

Abstract: In some examples, a mobile computing device is configured to receive electronic analog audio signals, generated by an input device responsive to receiving audio input, representing one or more words in a first language; digitize the electronic analog audio signal to produce a stream of digitized audio samples; encode, with a voice encoder of the mobile computing device, the stream of digitized audio samples to generate one or more encoded voice packets; send the one or more encoded voice packets to a remote voice translation service; receive, from the remote voice translation service, one or more encoded translated voice packets, wherein the one or more encoded translated voice packets represent one or more words in a second language translated from the one or more words in the first language; and output the one or more encoded translated voice packets via a cellular communication session over a cellular network.

Abstract: A mobile terminal including a display; a proximity sensor configured to sense a predetermined action of a user; an audio output unit; and a controller configured to deactivate the display and enter the mobile terminal into a standby mode while maintaining the proximity sensor in an activated state, and in response to the proximity sensor sensing the predetermined action by the user, output audio data through the audio output unit while the display is deactivated corresponding to information collected about a previous event that occurred on the mobile terminal.

Abstract: A terminology marker system integrates a terminology analytical component for quantifying the amount of linguistic noise found in the translation output as measured against a dictionary; further, correlating the noise measured on a continuous basis enables the analytical component to build terminology predictive models used in a feedback loop to upstream components of the supply chain to improve future translation of new content. The system also provides a smart terminology assessment component for assessing linguistic assets and improving the quality of those assets to assist in translation. The system also provides a smart terminology evaluation component that is able to analyze MT output to make smart decisions on reducing the amount of post editing corrections needed for delivering a persistent level of translation quality.

Abstract: A vector joint encoding/decoding method and a vector joint encoder/decoder are provided, more than two vectors are jointly encoded, and an encoding index of at least one vector is split and then combined between different vectors, so that encoding idle spaces of different vectors can be recombined, thereby facilitating saving of encoding bits, and because an encoding index of a vector is split and then shorter split indexes are recombined, thereby facilitating reduction of requirements for the bit width of operating parts in encoding/decoding calculation.

Abstract: A method and apparatus that dynamically adjust operational parameters of a text-to-speech engine in a speech-based system are disclosed. A voice engine or other application of a device provides a mechanism to alter the adjustable operational parameters of the text-to-speech engine. In response to one or more environmental conditions, the adjustable operational parameters of the text-to-speech engine are modified to increase the intelligibility of synthesized speech.

Abstract: An interactive voice response (IVR) system comprises a memory storing recorded segments of speech by individuals, and a processor configured to enroll individuals. The enrollment process may comprise retrieving one or more of said recorded segments of speech by an individual from said memory and using the retrieved segments to create a voice print for the individual. The suitability of the voice print for authenticating the individual in an IVR system is then tested. This may be done using segments of speech of a predetermined maximum duration such as three seconds or some other amount commensurate with the typical duration of a voice response in an IVR system. An individual may be enrolled as suitable for IVR authentication if the voice print passed the suitability test. Individuals may be authenticated using a voice print only if the voice print has passed the suitability test.

Abstract: To guide a conversation based on cognitive analytics, data of the conversation up to a time in the conversation is received from a conversation interface while the conversation is continuing. Current data is received from a data source. The current data relates to a remote participant in the conversation and a topic in the conversation. A sentiment value of the remote participant during the conversation is determined from the current data and the conversation data. While the conversation is continuing, data of a prompt is introduced into the conversation. The data of the prompt is configured to cause the conversation to increase the sentiment value of the remote participant. A profile of the remote participant is updated with the sentiment value, to form an updated profile. The updated profile is used as a second data source in a later portion of the conversation.

Abstract: Combining the natural language processing of product descriptions and statistical analysis of payment data to classify consumers based on products purchased and merchants based on products sold. Systems and methods use natural language processing techniques to interpret the descriptions of item level purchase data to classify products that have been purchased by customers into micro-categories. Statistical deviation methods are applied to the payment data to calculate normalized mean product cost, after removing outliers. After determining the micro-categories of the products purchased and the mean product cost of the purchased products, the system and methods classify consumers and merchants into categories based at least in part on the product micro-categories, mean costs, and relative volume of product types sold by merchants to predict which consumers are likely to purchase from which merchants.

Abstract: Methods and systems for identifying sound from a source of interest are provided for herein. In some embodiments, a first audio feed is captured by a first microphone and a second audio feed is captured by a second microphone. The first microphone may be located closer in proximity to the source of interest than the second microphone. The first audio feed can be processed utilizing the second audio feed to produce a first processed audio feed that can enable identification of sound originating from the source of interest. In some embodiments, the second audio feed can be additionally processed utilizing the first audio feed to produce a second processed audio feed. In such embodiments, frequencies from the first processed audio feed can be compared against frequencies of the second processed audio feed to identify sound originating from the source of interest. Other embodiments may be described and/or claimed herein.

Abstract: An information processing system is configured to: acquire a plurality of converted character strings one by one, each of the plurality of converted character strings having been converted from a corresponding one of a plurality of original character strings included in an original image; generate, each time a converted character string is acquired, a converted image representing the converted character string for the original image corresponding to the acquired converted character string; and change a content of a foreground of an arrangement area of the original image in an object to be displayed on a screen to the converted image.

Abstract: According to some aspects, a method of associating dictation with an electronic record in a system having a dictation system comprising a dictation application for capture of speech input and a separate electronic records system for managing electronic records is provided. The method comprises receiving, by the dictation application, speech input from a user corresponding to a dictation to be associated with an electronic record of the electronic records system, obtaining, by the dictation application, a job identifier associated with the dictation, providing, by the dictation application, the job identifier and audio data based on the speech input for transcription, obtaining, by the dictation application, a dictation marker comprising the job identifier and one or more delimiters, and causing the dictation marker to be inserted into the electronic record.

Abstract: According to some embodiments of the present invention, there is provided a computerized method for selecting and correcting pitch marks in speech processing and modification. The method comprises an action of receiving a continuous speech signal representing audible speech recorded by a microphone, where a sequence of pitch values and two or more pitch mark temporal values are computed from the continuous speech signal. The method comprises an action of computing for each of the pitch mark temporal values a lower limit temporal value and an upper limit temporal value by a cross-correlation function of the continuous speech signal around the pitch mark temporal values associated with pairs of elements in the sequence and replacing one or more of the pitch mark temporal values with one or more new temporal value between the lower limit temporal value and the upper limit temporal value.

Abstract: Speech generating devices, communication systems, and methods for communicating using the devices and systems are disclosed herein. In certain examples, the speech generating device includes: a first display device positioned in a first direction, the first display device configured to face a user of the speech generating device; an input device configured to generate a communication to be displayed on the first display device; and a second display device positioned in a second direction different from the first direction, wherein the second display device is configured to display a social cue proxy or an emotional proxy of the generated communication.

Abstract: Topics of potential interest to a user, useful for purposes such as targeted advertising and product recommendations, can be extracted from voice content produced by a user. A computing device can capture voice content, such as when a user speaks into or near the device. One or more sniffer algorithms or processes can attempt to identify trigger words in the voice content, which can indicate a level of interest of the user. For each identified potential trigger word, the device can capture adjacent audio that can be analyzed, on the device or remotely, to attempt to determine one or more keywords associated with that trigger word. The identified keywords can be stored and/or transmitted to an appropriate location accessible to entities such as advertisers or content providers who can use the keywords to attempt to select or customize content that is likely relevant to the user.

Abstract: System, apparatus and method for determining semantic information from audio, where incoming audio is sampled and processed to extract audio features, including temporal, spectral, harmonic and rhythmic features. The extracted audio features are compared to stored audio templates that include ranges and/or values for certain features and are tagged for specific ranges and/or values. The semantic information may be associated with audio codes to determine changing characteristics of identified media during a time period.

Abstract: A text sentence is automatically converted to an image sentence that conveys semantic roles of the text sentence. This is accomplished by identifying semantic roles associated with each verb of a sentence, any associated verb adjunctions, and identifying the grammatical dependencies between words and phrases in a sentence, in some embodiments. An image database, in which each image is tagged with descriptive information corresponding to the image depicted, is queried for images corresponding to the semantic roles of the identified verbs. Unless a single image is found to depict every semantic role, the text sentence is split into two smaller fragments. This process is the repeated and performed recursively until a number of images have been identified that describe each semantic role of each sentence fragment.

Abstract: Method for text-dependent Speaker Recognition using a speaker adapted Universal Background Model, wherein the speaker adapted Universal Background Model is a speaker adapted Hidden Markov Model comprising channel correction.

Abstract: A vehicle based system and method for receiving voice inputs and determining whether to perform a voice recognition analysis using in-vehicle resources or resources external to the vehicle.