Abstract: A dialogue system and a method for the same are disclosed. The dialogue system includes a multimodal input unit receiving speech and non-speech information of a user, a domain reasoner, which stores a plurality of pre-stored situations, each of which is formed by a combination one or more speech and non-speech information, calculating each adaptability of the pre-stored situations on the basis of a generated situation based on the speech and the non-speech information received from the multimodal input unit, and determining a current domain according to the calculated adaptability, a dialogue manager to select a response corresponding to the current domain, and a multimodal output unit to output the response. The dialogue system performs domain reasoning using a situation including information combinations reflected in the domain reasoning process, current information, and a speech recognition result, and reduces the size of a dialogue search space while increasing domain reasoning accuracy.

Abstract: A scribe system is provided. The scribe system includes a server operating a software product and a plurality of recording devices for recording speech of a user into a recorded audio file. The scribe system also includes a network connection between the server and the plurality of recording devices. Each recording device transfers the recorded audio file to the server through the network connection in response to completion of recording the audio file. The server confirms successful transmission to the recording device in response to operation of the software product.

Abstract: A system and method for an integrated, multi-modal, multi-device natural language voice services environment may be provided. In particular, the environment may include a plurality of voice-enabled devices each having intent determination capabilities for processing multi-modal natural language inputs in addition to knowledge of the intent determination capabilities of other devices in the environment. Further, the environment may be arranged in a centralized manner, a distributed peer-to-peer manner, or various combinations thereof. As such, the various devices may cooperate to determine intent of multi-modal natural language inputs, and commands, queries, or other requests may be routed to one or more of the devices best suited to take action in response thereto.

Abstract: A method for voice modification during a telephone call comprising receiving a source audio signal associated with at least one participant, wherein the source audio signal comprises a voice of the at least one participant, detecting a source dialect of the at least one participant, selecting a target dialect based on at least a characteristic of a target participant and creating a modulated audio signal based on the source audio signal, the source dialect, and the target dialect and transmitting the modulated audio signal to the target participant.

Abstract: An intelligent conversation system augmenting a conversation between two or more individuals uses a speech to text block configured to convert voices of the conversation into text, a determination circuit configured to determine topics from the text of the conversation, search parameters determined by the determination circuit from the topics are sent to an Internet, search results corresponding to the search parameters are received from the Internet; and a memory configured to store the search results received from the Internet. The speech to text block is configured to convert the search results to speech. An earphone is configured to transmit the speech to one of the two or more individuals. The speech is used by one of the individuals to augment the conversation.

Abstract: A method and apparatus of suppressing a vocoder noise are provided. The method includes receiving from a channel decoder a vocoder frame and first information, the first information indicating whether the vocoder frame has an error, generating speech data by performing voice decoding on the vocoder frame, determining whether a tonal noise has been detected in the speech data, if the first information indicates that the vocoder frame has an error, and attenuating the volume of the speech data and outputting the volume-attenuated speech data through a speaker, upon detection of the tonal noise in the speech data.

Abstract: Methods and systems are provided for generating automatic program recommendations based on user interactions. In some embodiments, control circuitry processes verbal data received during an interaction between a user of a user device and a person with whom the user is interacting. The control circuitry analyzes the verbal data to automatically identify a media asset referred to during the interaction by at least one of the user and the person with whom the user is interacting. The control circuitry adds the identified media asset to a list of media assets associated with the user of the user device. The list of media assets is transmitted to a second user device of the user.

Abstract: An audio encoder has a window function controller, a windower, a time warper with a final quality check functionality, a time/frequency converter, a TNS stage or a quantizer encoder, the window function controller, the time warper, the TNS stage or an additional noise filling analyzer are controlled by signal analysis results obtained by a time warp analyzer or a signal classifier. Furthermore, a decoder applies a noise filling operation using a manipulated noise filling estimate depending on a harmonic or speech characteristic of the audio signal.

Abstract: Techniques for authenticating users at devices that interact with the users via voice input. For instance, the described techniques may allow a voice-input device to safely verify the identity of a user by engaging in a back-and-forth conversation. The device or another device coupled thereto may then verify the accuracy of the responses from the user during the conversation, as well as compare an audio signature associated with the user's responses to a pre-stored audio signature associated with the user. By utilizing multiple checks, the described techniques are able to accurately and safely authenticate the user based solely on an audible conversation between the user and the voice-input device.

Abstract: Embodiments of the present invention address deficiencies of the art in respect to virtualization and provide a novel and non-obvious method, system and computer program product for annotation of street grammar in speech enabled navigation devices. In an embodiment of the invention, a pre-processing street grammar annotation system can be provided. The system can include an annotated street grammar storage that contains street root names wherein each street root name has more than one street suffix associated with said street root name, and a street annotation pre-processor wherein the street annotation pre-processor contains logic enabled to annotate a set of street suffixes to a street root name prior to processing a voice input in a speech enabled navigation device, wherein the street root name has more than one street suffix associated with said street root name.

Abstract: Natural language controlled devices may be configured to activate command recognition in response to one or more wake words. Techniques are provided to receive a candidate word for evaluation as a wake word that activates a natural language control functionality of a computing device. The candidate word may include one or more words or sounds. Values for multiple wake word metrics are then determined. The candidate word is evaluated based on the various wake word metrics.

Abstract: A language processing system identifies, from log data, command inputs that parsed to a parsing rule associated with an action. If the command input has a signal indicative of user satisfaction, where the signal is derived from data that is not generated from performance of the action (e.g., user interactions with data provided in response to the performance of another, different action; resources identified in response to the performance of another, different action having a high quality score; etc.), then exception data is generated for the parsing rule. The exception data specifies the particular instance of the sentence parsed by the parsing rule, and precludes invocation of the action associated with the rule.

Abstract: Methods and devices for a low complex inter-channel difference estimation are provided. A method for the estimation of inter-channel differences (ICDs), comprises applying a transformation from a time domain to a frequency domain to a plurality of audio channel signals, calculating a plurality of ICD values for the ICDs between at least one of the plurality of audio channel signals and a reference audio channel signal over a predetermined frequency range, each ICD value being calculated over a portion of the predetermined frequency range, calculating, for each of the plurality of ICD values, a weighted ICD value by multiplying each of the plurality of ICD values with a corresponding frequency-dependent weighting factor, and calculating an ICD range value for the predetermined frequency range by adding the plurality of weighted ICD values.

Abstract: Semantic clustering techniques are described. In various implementations, a conversational agent is configured to perform semantic clustering of a corpus of user utterances. Semantic clustering may be used to provide a variety of functionality, such as to group a corpus of utterances into semantic clusters in which each cluster pertains to a similar topic. These clusters may then be leveraged to identify topics and assess their relative importance, as for example to prioritize topics whose handling by the conversation agent should be improved. A variety of utterances may be processed using these techniques, such as spoken words, textual descriptions entered via live chat, instant messaging, a website interface, email, SMS, a social network, a blogging or micro-blogging interface, and so on.

Abstract: Methods and systems for identifying conditional actions in a business process are disclosed. In accordance with one such method, text fragments are extracted from input documents. In addition, a plurality of pairs of the text fragments that respectively include text fragments that are similar according to a pre-defined similarity standard are determined. For each pair of at least a subset of the pairs, at least one difference between the text fragments of the corresponding pair is determined. Further, at least two particular pairs of the subset of the pairs are merged in response to determining that the particular pairs have at least one of the determined differences in common. Additionally, the merged particular pairs are output to indicate the conditional actions in the business process.

Abstract: An audio encoder has a window function controller, a windower, a time warper with a final quality check functionality, a time/frequency converter, a TNS stage or a quantizer encoder, the window function controller, the time warper, the TNS stage or an additional noise filling analyzer are controlled by signal analysis results obtained by a time warp analyzer or a signal classifier. Furthermore, a decoder applies a noise filling operation using a manipulated noise filling estimate depending on a harmonic or speech characteristic of the audio signal.

Abstract: A system and method are disclosed that improve automatic speech recognition in a spoken dialog system. The method comprises partitioning speech recognizer output into self-contained clauses, identifying a dialog act in each of the self-contained clauses, qualifying dialog acts by identifying a current domain object and/or a current domain action, and determining whether further qualification is possible for the current domain object and/or current domain action. If further qualification is possible, then the method comprises identifying another domain action and/or another domain object associated with the current domain object and/or current domain action, reassigning the another domain action and/or another domain object as the current domain action and/or current domain object and then recursively qualifying the new current domain action and/or current object. This process continues until nothing is left to qualify.

Abstract: A word pattern recognition system improves text input entered via a shorthand-on-keyboard interface. A core lexicon comprises commonly used words in a language; an extended lexicon comprises words not included in the core lexicon. The system only directly outputs words from the core lexicon. Candidate words from the extended lexicon can be outputted and simultaneously admitted to the core lexicon upon user selection. A concatenation module enables a user to input parts of a long word separately. A compound word module combines two common shorter words whose concatenation forms a long word.

Abstract: A computer implemented machine translation system and method is provided that improves the accuracy of output from one or more machine translation systems by applying one or more data correction routines. A data correction routine is provided that includes information distance analysis of one or more sets of machine translation information to a set of text elements related to the domain and stored to a database. The system and method generate as output corrected text elements related to a meaning intended by a user from whom the machine translation information was captured.

Abstract: Methods and a system for calculating N-gram probabilities in a language model. A method includes counting N-grams in each page of a plurality of pages or in each document of a plurality of documents to obtain respective N-gram counts therefor. The method further includes applying weights to the respective N-gram counts based on at least one of view counts and rankings to obtain weighted respective N-gram counts. The view counts and the rankings are determined with respect to the plurality of pages or the plurality of documents. The method also includes merging the weighted respective N-gram counts to obtain merged weighted respective N-gram counts for the plurality of pages or the plurality of documents. The method additionally includes calculating a respective probability for each of the N-grams based on the merged weighted respective N-gram counts.