Abstract: An editing method facilitates the task of adding background sound to speech-containing audio data so as to augment the listening experience. The editing method is executed by a processor in a computing device and comprises obtaining characterization data that characterizes time segments in the audio data by at least one of topic and sentiment; deriving, for a respective time segment in the audio data and based on the characterization data, a desired property of a background sound to be added to the audio data in the respective time segment, and providing the desired property for the respective time segment so as to enable the audio data to be combined, within the respective time segment, with background sound having the desired property. The background sound may be selected and added automatically or by manual user intervention.

Abstract: The systems, devices, and processes described herein may asynchronously transfer audio signals from a voice-controlled device to a remote device. The audio signals may correspond to sound that is captured by multiple microphones of the voice-controlled device, which may then process the audio signals. The audio signals may also be transferred to the remote device for processing. Moreover, a determination of whether the voice-controlled device or the remote device is to process the audio signals may be based at least in part on the bandwidth of a network communicatively coupled to the voice-controlled device. The voice-controlled device may also cache and log the audio signals, and then asynchronously stream the audio signals to the remote device after the audio signals are initially processed, which may be based on the bandwidth of the network. The remote device may utilize the unprocessed audio signals to improve subsequent processing of audio signals.

Abstract: Systems and methods are utilized for recognizing speech that is partially in a foreign language. The systems and methods receive speech input from a user and detect if a rule or sentence entry grammar structure utilizing a foreign word has been uttered. To recognize the foreign word, a foreign word grammar is utilized. The foreign word grammar includes rules for recognizing the uttered foreign word. Two rules may be included in the foreign word grammar for each legitimate or slang term included in the foreign word grammar. A first rule corresponds to the spoken form of the foreign word, and the second rule corresponds to the spelling form of the foreign word. The foreign word grammar may also utilize a prefix tree. Upon recognizing the foreign word, the recognized foreign word may be sent to an application to retrieve the pronunciation, translation, or definition of the foreign word.

Abstract: An audio mixer for mixing audio signals from a plurality of participants, including audio signals of different sample rates; the audio mixer comprising: a plurality of mixing arrangements, each mixing arrangement for a given one of said sample rates; each mixing arrangement comprising: a pre-mixer configured to mix audio signals having the given sample rate; one or more resamplers, each resampler configured to convert pre-mixed audio signals from other mixing arrangements into a signal of the given sample rate; and a post-mixer configured to mix the output of the pre-mixer with the output of each resampler to produce an output at the given sample rate; the audio mixer further comprising a subtractor configured to subtract the participant's input audio signal from the post-mixed output.

Abstract: A method, an apparatus and a system for recognizing an evaluation element are provided. The method includes receiving an input text; performing, using a first conditional random field model, first recognition for the input text to obtain a first recognition result, the first recognition result including a pre-evaluation element that is recognized by using the first conditional random field model; performing, using a second conditional random field model, second recognition for the input text to obtain a second recognition result, the second recognition result including a false positive evaluation element that is recognized by using the second conditional random field model, the false positive evaluation element being an element erroneously detected as an evaluation element; and recognizing, based on the first recognition result and the second recognition result, an evaluation element in the input text.

Abstract: A method for mapping a source lexical unit in a first language with target lexical unit in a second language, the method comprising: acquiring a source digital text comprising a plurality of source sentences; parsing the plurality of source sentences into source lexical units; generating, for each of the one or more source lexical units a source context parameter; acquiring a target digital text comprising a plurality of target sentences; parsing the plurality of target sentences into target lexical units; generating for each one or more target lexical units, a target context parameter; selecting a first source lexical unit having a first source context parameter; comparing the first source context parameter with a plurality of target context parameters to determine a target context parameter having a lowest difference value; mapping the first source lexical unit with a first target lexical unit associated with the given target context parameter.

Abstract: Systems, methods, and computer program products relate to special effects for a text source, such as a traditional paper book, e-book, mobile phone text, comic book, or any other form of pre-defined reading material, and for outputting the special effects. The special effects may be played in response to a user reading the text source aloud to enhance their enjoyment of the reading experience and provide interactivity. The special effects can be customized to the particular text source and can be synchronized to initiate the special effect in response to pre-programmed trigger phrases when reading the text source aloud.

Abstract: Methods and a natural language processor for processing a natural language query are provided. The processor includes a classifier, a rule-based pre-processor, a rule-based post-processor, a named entity recognizer, and an output module. The method involves receiving a text representation of the natural language query, pre-processing the text representation, applying a classification statistical model to the text representation when pre-processing fails, applying a post-processing rule, and performing name entity recognition.

Abstract: A method for using voiceprint identification to operate voice recognition and electronic device thereof are provided. The method includes the following steps: receiving a specific voice fragment; cutting the received specific voice fragment into a plurality of specific sub-voice clips; performing a voiceprint identification flow to the specific sub-voice clips, respectively; determining whether each of the specific sub-voice clips is an appropriate sub-voice clip according to a result of the voiceprint identification flow; and capturing the appropriate sub-voice clips and operating a voice recognition thereto.

Abstract: A method for maintaining conversational cadence may include determining, by a processor, a conversational cadence associated with a user in a social network. The conversational cadence may be determined based on a plurality of messages previously transmitted by the user. The method may also include detecting, by the processor, a reduction in the conversational cadence of the user. The method may further include providing, by the processor, a set of fill-in messages that create an appearance to another user in the social network that there is no reduction in the conversational cadence.

Abstract: Provided is a system, method and computer-readable medium for generating data that may be used to train models for a natural language processing application. A system architect creates a plurality of sentence patterns that include entity variables and initiates sentence generation. Each entity is associated with one or more entity data sources. A language generator accepts the sentence patterns as inputs, and references the various entity sources to create a plurality of generated sentences. The generated sentences may be associated with a particular class and therefore used to train one or more statistical classification models and entity extraction models for associated models. The sentence generated process may be initiated and controlled using a user interface displayable on a computing device, the user interface in communication with the language generator module.

Abstract: A recording system has a listener processor for automatically capturing events involving computer applications during a dialog involving the user of the computer. The system generates a visual transcript of events on a timeline. It automatically detects start of a dialog and proceeds to detect events and determines if they are configured as transcript events, before detecting end of the dialog. The system may associate dialog events with audio clips, using meta tags.

Abstract: Increasing the level of the consonant segments relative to the nearby vowel segments, known as consonant-vowel ratio (CVR) modification, is reported to be effective in improving speech intelligibility by listeners in noisy backgrounds and by hearing-impaired listeners. A method along with a system for real-time CVR modification using the rate of change of spectral centroid for detection of spectral transitions is disclosed. A preferred embodiment of the invention using a 16-bit fixed point processor with on-chip FFT hardware is also presented for real-time signal processing. It can be integrated with other FFT-based signal processing in communication devices, hearing aids, and other systems for improving speech perception under adverse listening conditions.

Abstract: A method is provided for processing attenuation of pre-echo in a digital audio signal decoded by transform decoding. The method includes the following acts: decomposition of the decoded signal into at least two sub-signals according to a pre-determined decomposition criterion; calculation of attenuation factors per sub-signal and per sample of a previously determined pre-echo zone; attenuation of pre-echo in the pre-echo zone of each of the sub-signals by applying attenuation factors to the sub-signals; and production of the attenuated signal by addition of the attenuated sub-signals. Also provided are a processing device implementing the acts of the described method, and a decoder including such a device.

Abstract: Systems, methods and apparatus for invoking actions at a second user device from a first user device. A method includes determining that a first user device has an associated second user device; accessing specification data that specifies a set of user device actions that the second user device is configured to perform; receiving command inputs for the first user device; for each command input, determining whether the command input resolves to one of the user device actions; for each command input not determined to resolve to any of the user device actions, causing the command input to be processed at the first user device; and for each command input determined to resolve one of the user device actions causing the first user device to display in a user interface a dialog by which a user may either accept or deny invoking the user device action at the second user device.

Abstract: A system includes a server and an image processing apparatus, and the server is provided that includes a communication interface, a storage, and a processor. The communication interface is configured to communicate with the image processing apparatus. The storage is configured to store data. The processor may provide a result of processing a first event that includes a speech of a user to the image processing apparatus in response to the first event being received from the image processing apparatus, store a record of the first event in the storage according to processing of the first event, determine a relation between the first and second events that includes a user input by a non-speech method in response to the second event being received from the image processing apparatus, and process the second event based on the record of the first event stored in the storage in response to the relation.

Abstract: Computer implemented systems and methods of processing clinical documentation for a multi-axial coding scheme include inputting clinical documentation from memory operatively coupled with a computer system, and executing a natural language processor configured to process narrative text in the clinical documentation. The processor segments the narrative text based on boundaries defined in the clinical documentation, sequences words in the narrative text based on the segmentation, and maps the sequenced words to semantic objects in an ontology database. The ontology defines classes of semantic objects and relationships between them, corresponding to the multi-axial coding scheme. The semantic objects are converted into characters and output into slots in a medical code, with the characters positioned in the slots based on the multi-axial coding scheme.

Abstract: One or more processors identify one or more character errors in a document. The one or more processors replace a character having the identified one or more character errors with a replacement character. The replacement of the character error with the replacement character allows deep parsing of the document to complete. The one or more processors apply to the document one or both of a deep parsing and natural language processing after the replacing.

Abstract: A method includes determining a preprocessed audio signal by removing some noise from an input audio signal. Here, portions of the preprocessed audio signal that include speech are separated by portions of the preprocessed audio signal that include residual noise. Additionally, the method includes determining an amplified signal by suppressing the preprocessed audio signal over the portions that include residual noise, and maintaining the preprocessed audio signal over the portions that include speech.

Abstract: Technology is disclosed to select a preferred machine translation from multiple machine translations of a content item, each machine translation from the multiple machine translations created for the same target language. Each machine translation is assigned a score based on feedback from a user group that receives the machine translation. The machine translation with the highest score is identified as the preferred machine translation, and is provided in response to subsequent requests for translations of the content item. If there is no preferred translation, the several top scoring machine translations are provided to a larger group of users for further scoring. This process may be repeated until either a clearly preferred translation is identified, a maximum number of iterations is reached, or a maximum number of scoring users is reached.