Abstract: Question Answering systems can be costly and time-consuming to configure for a particular knowledge base. The proposed Question Answering receives an initial knowledge base, receives user queries without any further configuration, and self-configures based on user feedback. In one embodiment, a method of customizing a question answering system can include searching a plurality of articles based on a user query from a user received via a computer network. The method can further include delivering a set of articles, based on the searching, to the user via the computer network. The method can additionally include receiving user feedback on the set of articles from the user via the computer network. The method can also include associating a given article from among the set of articles with the user query based on the user feedback. In this manner, the proposed question answering system saves the customer resources otherwise spent on configuration.

Abstract: The present invention uses natural language understanding to increase the ability of a customer service system to respond to a user's query in an automated manner. A customer service system receives a query from a user and offers the user the option of having the system contact the user at a later time with an answer. If the user accepts the offer, the customer service system processes the query offline, including providing the query to a natural language understanding interpreter. The system uses the natural language understanding interpretation to determine if the user's query is in a database of frequently-asked queries. For each query in the database of frequently-asked queries, there is a predetermined response protocol. If the user's query substantially matches a query in the database, the IVR system contacts the user with an automated response in accordance with the predetermined response protocol for the query.

Abstract: Presentation of results of a predictive analysis of text is delayed until entry of the text by a user is paused by a particular amount of time. The results are available for selection by the user for another particular amount of time. After the other particular amount of time is expired, the results are no longer available to for selection. If a particular result is selected, the selected result either replaces or supplements the entered text.

Abstract: A method for enhancing a media file to enable speech-recognition of spoken navigation commands can be provided. The method can include receiving a plurality of textual items based on subject matter of the media file and generating a grammar for each textual item, thereby generating a plurality of grammars for use by a speech recognition engine. The method can further include associating a time stamp with each grammar, wherein a time stamp indicates a location in the media file of a textual item corresponding with a grammar. The method can further include associating the plurality of grammars with the media file, such that speech recognized by the speech recognition engine is associated with a corresponding location in the media file.

Abstract: A Natural Language Understanding system is provided for indexing of free text documents. The system according to the invention utilizes typographical and functional segmentation of text to identify those portions of free text that carry meaning. The system then uses words and multi-word terms and phrases identified in the free to text to identify concepts in the free text. The system uses a lexicon of terms linked to a formal ontology that is independent of a specific language to extract concepts from the free text based on the words and multi-word terms in the free text. The formal ontology contains both language independent domain knowledge concepts and language dependent linguistic concepts that govern the relationships between concepts and contain the rules about how language works. The system according to the current invention may preferably be used to index medical documents and assign codes from independent coding systems, such as, SNOMED, ICD-9 and ICD-10.

Abstract: The present invention relates to a signal processing system, comprising a number of microphones and loudspeakers, a hands-free set configured to receive a telephone signal from a remote party and to transmit a microphone signal supplied by at least one of the microphones to the remote party; an in-vehicle communication system configured to receive a microphone signal supplied by at least one of the microphones; receive the telephone signal; amplify the microphone signal to obtain at least one first output signal; output the at least one first output signal and/or a second output signal corresponding to the telephone signal to at least one of the loudspeakers; and wherein the signal processing systems is configured to detect speech activity in the telephone signal and to control the in-vehicle communication system to reduce amplification of the microphone signal by a damping factor, if it is detected that speech activity is present in the telephone signal.

Abstract: Establishing a multimodal personality for a multimodal application, including evaluating, by the multimodal application, attributes of a user's interaction with the multimodal application; selecting, by the multimodal application, a vocal demeanor in dependence upon the values of the attributes of the user's interaction with the multimodal application; and incorporating, by the multimodal application, the vocal demeanor into the multimodal application.

Abstract: A phonetic vocabulary for a speech recognition system is adapted to a particular speaker's pronunciation. A speaker can be attributed specific pronunciation styles, which can be identified from specific pronunciation examples. Consequently, a phonetic vocabulary can be reduced in size, which can improve recognition accuracy and recognition speed.

Abstract: The present invention relates to a method and apparatus for explicit filtering in ambiguous text entry. The invention provides embodiments including various explicit text entry methodologies, such as 2-key and long pressing. The invention also provides means for matching words in a database using build around methodology, stem locking methodology, word completion methodology, and n-gram searches.

Abstract: Embodiments of the present invention exploit redundancy of succeeding FFT spectra and use this redundancy for computing interpolated temporal supporting points. An analysis filter bank converts overlapped sequences of an audio (ex. loudspeaker) signal from a time domain to a frequency domain to obtain a time series of short-time loudspeaker spectra. An interpolator temporally interpolates this time series. The interpolation is fed to an echo canceller, which computes an estimated echo spectrum. A microphone analysis filter bank converts overlapped sequences of an audio microphone signal from the time domain to the frequency domain to obtain a time series of short-time microphone spectra. The estimated echo spectrum is subtracted from the microphone spectrum. Further signal enhancement (filtration) may be applied. A synthesis filter bank converts the filtered microphone spectra to the time domain to generate an echo compensated audio microphone signal.

Abstract: A machine, system and method for user-guided teaching and modifications of voice commands and actions to be executed by a conversational learning system. The machine includes a system bus for communicating data and control signals received from the conversational learning system to a computer system, a vehicle data and control bus for connecting devices and sensors in the machine, a bridge module for connecting the vehicle data and control bus to the system bus, machine subsystems coupled to the vehicle data and control bus having a respective user interface for receiving a voice command or input signal from a user, a memory coupled to the system bus for storing action command sequences learned for a new voice command and a processing unit coupled to the system bus for automatically executing the action command sequences learned when the new voice command is spoken.

Abstract: In one aspect, a method of processing a voice signal to extract information to facilitate training a speech synthesis model is provided. The method comprises acts of detecting a plurality of candidate features in the voice signal, performing at least one comparison between one or more combinations of the plurality of candidate features and the voice signal, and selecting a set of features from the plurality of candidate features based, at least in part, on the at least one comparison. In another aspect, the method is performed by executing a program encoded on a computer readable medium. In another aspect, a speech synthesis model is provided by, at least in part, performing the method.

Abstract: Methods and systems for multi level quality checking of transcripts are disclosed.

Abstract: The present invention provides a system, method, and computer program product for automatically detecting any unnecessary repetition by customers of specific types of information in a multi-channel (e.g., self-service application, IVR system, live agent center) customer service session. For each channel used in the customer service session, the information provided by the customer in the channel is recorded in a log, transcription, or other record. The record(s) for the customer service session are subsequently parsed for specific types of information provided by the customer. From the parsed records, specific types of information provided by the customer in two or more channels during the customer service session are identified. In one embodiment, the results are analyzed to determine if providing such information in two or more channels is redundant, and, if so, this is counted as a redundancy.

Abstract: A hardware and/or software search facility for searching and retrieving data stored on a mobile device. An index to the data is stored in fast memory (e.g., RAM) on the mobile device. The index contains a minimal amount of information necessary to present search results to a user. A supplemental data file is stored in storage that is local to or remote from the mobile device. The supplemental data files contain additional organized data that may be used to enhance the search results. In response to a search query, the facility uses the index to identify results that are responsive to the search query. The results are presented by the facility in accordance with predetermined rules. The facility may use the supplemental data file to perform further processing and present additional information. In some embodiments, the facility may mount or unmount indices and supplemental files from a device.

Abstract: Some embodiments relate to performing a search for content via the Internet, wherein user input specifying a search query is supplied to a mobile communications device, such as, for example, a smartphone. The mobile communications device separately issues the search query to a plurality of search engines and can receive the results from each search engine and display the results to the user. Thus, the user does not have to separately issue the query to each of the plurality of search engines.

Abstract: The invention provides a method for determining a noise reference signal for noise compensation and/or noise reduction. A first audio signal on a first signal path and a second audio signal on a second signal path are received. The first audio signal is filtered using a first adaptive filter to obtain a first filtered audio signal. The second audio signal is filtered using a second adaptive filter to obtain a second filtered audio signal. The first and the second filtered audio signal are combined to obtain the noise reference signal. The first and the second adaptive filter are adapted such as to minimize a wanted signal component in the noise reference signal.

Abstract: Techniques for combining the results of multiple recognizers in a distributed speech recognition architecture. Speech data input to a client device is encoded and processed both locally and remotely by different recognizers configured to be proficient at different speech recognition tasks. The client/server architecture is configurable to enable network providers to specify a policy directed to a trade-off between reducing recognition latency perceived by a user and usage of network resources. The results of the local and remote speech recognition engines are combined based, at least in part, on logic stored by one or more components of the client/server architecture. An indication of the availability of the remote speech recognition to perform speech recognition at a point in time may be provided to a user of the client device via a user interface of the client device.

Abstract: A speech output is generated from a text input written in a first language and containing inclusions in a second language. Words in the native language are pronounced with a native pronunciation and words in the foreign language are pronounced with a proficient foreign pronunciation. Language dependent phoneme symbols generated for words of the second language are replaced with language dependent phoneme symbols of the first language, where said replacing includes the steps of assigning to each language dependent phoneme symbol of the second language a language independent target phoneme symbol, mapping to each one language independent target phoneme symbol a language independent substitute phoneme symbol assignable to a language dependent substitute phoneme symbol of the first language, substituting the language dependent phoneme symbols of the second language by the language dependent substitute phoneme symbols of the first language.

Abstract: The present invention provides a system, method and software application for associating one or more phone numbers with an action on a phone and performing an action on the phone in response to the user initiating a call to one of such phone numbers. Certain phone numbers are associated with an action. The user's phone, or a server with which the user's phone communicates, maintains a table of the phone numbers associated with an action, and each phone number in the table is related to an action. Software on the user's phone listens for call initiated by a user. When the user initiates a call, software on the phone “intercepts” the call, and the phone (or a server with which the phone communicates) determines whether the call is to a phone number that is in the table. If the phone number is in the table, then it is associated with an action, and the user's phone performs that action at a time specified by instructions for such action.