Abstract: A parser for natural language text is provided. The parser is trained by accessing a corpus of labeled utterances. The parser extracts details of the syntactic tree structures and part of speech tags from the labeled utterances. The details extracted from the tree structures include Simple Links which are the key to the improved efficiency of this new approach. The parser creates a language model using the details that were extracted from the corpus. The parser then uses the language model to parse utterances.

Abstract: Building safety systems, methods, and mediums are provided. A method includes receiving a voice input by the building safety system. The method includes receiving voice data produced by a speech recognition process performed on the voice input. The method includes determining a response to the voice input based on the voice data. The method includes producing the response by the building safety system.

Abstract: An audio processor for processing an audio signal includes a target phase measure determiner for determining a target phase measure for the audio signal in a time frame, a phase error calculator for calculating a phase error using a phase of the audio signal in the time frame and the target phase measure, and a phase corrector configured for correcting the phase of the audio signal in the time frame using the phase error.

Abstract: In some implementations, (i) audio data representing a voice command spoken by a speaker and (ii) a speaker identification result indicating that the voice command was spoken by the speaker are obtained. A voice action is selected based at least on a transcription of the audio data. A service provider corresponding to the selected voice action is selected from among a plurality of different service providers. One or more input data types that the selected service provider uses to perform authentication for the selected voice action are identified. A request to perform the selected voice action and (i) one or more values that correspond to the identified one or more input data types are provided to the service provider.

Abstract: A method is described that estimates noise in an audio signal. An energy value for the audio signal is estimated and converted into the logarithmic domain. A noise level for the audio signal is estimated based on the converted energy value.

Abstract: An electronic device includes an audio synthesizer. The audio synthesizer can generate a voice-synthesized audio output stream as a function of one or more audible characteristics extracted from voice input received from an authorized user of the electronic device. The audio synthesizer can also apply an acoustic watermark to the voice-synthesized audio output stream, the acoustic watermark indicating that the voice-synthesized audio output stream is machine made.

Abstract: An electronic device includes an audio synthesizer. The audio synthesizer can generate a voice-synthesized audio output stream as a function of one or more audible characteristics extracted from voice input received from an authorized user of the electronic device. The audio synthesizer can also apply an acoustic watermark to the voice-synthesized audio output stream, the acoustic watermark indicating that the voice-synthesized audio output stream is machine made.

Abstract: Efficient empirical determination, computation, and use of an acoustic confusability measure comprises: (1) an empirically derived acoustic confusability measure, comprising a means for determining the acoustic confusability between any two textual phrases in a given language, where the measure of acoustic confusability is empirically derived from examples of the application of a specific speech recognition technology, where the procedure does not require access to the internal computational models of the speech recognition technology, and does not depend upon any particular internal structure or modeling technique, and where the procedure is based upon iterative improvement from an initial estimate; (2) techniques for efficient computation of empirically derived acoustic confusability measure, comprising means for efficient application of an acoustic confusability score, allowing practical application to very large-scale problems; and (3) a method for using acoustic confusability measures to make principled

Abstract: An electronic health record compatible dictation transcription system records and edits audio in an encrypted format. The system delineates audio for different electronic health record fields during dictation (i.e., recording and editing of the audio in the encrypted format), and the system inserts large predetermined text portions into transcriptions of dictated text in response to verbal prompts in the dictation audio.

Abstract: Techniques for improving machine learning and text classification are described. The described techniques include improved processes for collecting training data to train a machine classifier. Some data sets are very large but contain only a small number of positive or negative training examples. The described text classification system obtains training examples by intelligently identifying documents that are likely to present or identify positive or negative training examples. The text classification system employs these techniques to train a classifier to categorize patent claims according some legal rule, such as subject-matter eligibility requirements under patent law.

Abstract: Methods, systems, and apparatus for receiving, by a voice action system, data specifying trigger terms that trigger an application to perform a voice action and a context that specifies a status of the application when the voice action can be triggered. The voice action system receives data defining a discoverability example for the voice action that comprises one or more of the trigger terms that trigger the application to perform the voice action when a status of the application satisfies the specified context. The voice action system receives a request for discoverability examples for the application from a user device having the application installed, and provides the data defining the discoverability examples to the user device in response to the request. The user device is configured to provide a notification of the one or more of the trigger terms when a status of the application satisfies the specified context.

Abstract: Systems and methods for enhancing the depth and richness of content in computer-generated patent applications by providing non-explicit support for individual claim features are disclosed. Exemplary implementations may: receive a previously unseen claim feature, the previously unseen claim feature being absent from the previously received patent documents; provide one or more sentences of never-been-seen-before computer-generated text using the trained machine learning model and the previously unseen claim feature as input; and insert the one or more sentences of non-explicit support in a draft patent application proximal to explicit support for the previously unseen claim feature.

Abstract: Transportation of audio data is provided between a first network element and a second network element. The first network element divides multichannel audio data by channel into a plurality of individual channels. The first network element packages each of the plurality of individual channels together with a corresponding sampling set of audio data into a single packet. The first network element transmits to the second network element each packet that includes a channel having an active sampling set of audio data.

Abstract: An apparatus for selecting one of a first encoding algorithm and a second encoding algorithm includes a filter configured to receive the audio signal, to reduce the amplitude of harmonics in the audio signal and to output a filtered version of the audio signal. First and second estimators are provided for estimating first and second quality measures in the form of SNRs of segmented SNRs associated with the first and second encoding algorithms without actually encoding and decoding the portion of the audio signal using the first and second encoding algorithms. A controller is provided for selecting the first encoding algorithm or the second encoding algorithm based on a comparison between the first quality measure and the second quality measure.

Abstract: Disclosed are machine learning-based technologies that analyze an audio input and provide speaker state predictions in response to the audio input. The speaker state predictions can be selected and customized for each of a variety of different applications.

Abstract: A signal encoding method and device are disclosed. The method includes, when an encoding manner of a previous frame of a currently-input frame is a continuous encoding manner, predicting a comfort noise that is generated by a decoder according to the currently-input frame when the currently-input frame is encoded into an SID frame, determining an actual silence signal, determining a deviation degree between the comfort noise and the actual silence signal, determining an encoding manner of the currently-input frame according to the deviation degree, and encoding the currently-input frame according to the encoding manner of the currently-input frame. It is determined, according to the deviation degree between the comfort noise and the actual silence signal, that the encoding manner of the currently-input frame is the hangover frame encoding manner or the SID frame encoding manner, which can save communication bandwidth.

Abstract: An audio encoder for encoding segments of coefficients, the segments of coefficients representing different time or frequency resolutions of a sampled audio signal, the audio encoder including a processor for deriving a coding context for a currently encoded coefficient of a current segment based on a previously encoded coefficient of a previous segment, the previously encoded coefficient representing a different time or frequency resolution than the currently encoded coefficient. The audio encoder further includes an entropy encoder for entropy encoding the current coefficient based on the coding context to obtain an encoded audio stream.

Abstract: A method includes performing, with at least one processing device, natural language generation using both (i) a semantic word and clause representation generated from syntactically-labeled context and (ii) a syntax generated from common semantic relations between sequential words and clauses. Performing the natural language generation includes pushing words onto a stack based on the semantic word and clause representation and based on words and clauses already on the stack and popping the words and clauses off the stack to be replaced by clauses based on the syntax. Pushing the words onto the stack could be based only on components of the semantic word and clause representation coming from future context.

Abstract: Provided are a computer program product, system, and method for using remote words in data streams from remote devices to autocorrect input text. Remote words included in a at least one data stream are accessed from at least one remote device over a network to store in a remote word corpus. User input text is received in a text entry field in a user interface rendered by the computer device. Local words are maintained in a local word corpus stored in the computer device. The local words and the remote words are used to autocorrect and validate the user input text.

Abstract: A non-transitory processor-readable medium storing code representing instructions to be executed by a processor includes code to cause the processor to receive acoustic data representing an utterance spoken by a language learner in a non-native language in response to prompting the language learner to recite a word in the non-native language and receive a pronunciation lexicon of the word in the non-native language. The pronunciation lexicon includes at least one alternative pronunciation of the word based on a pronunciation lexicon of a native language of the language learner. The code causes the processor to generate an acoustic model of the at least one alternative pronunciation in the non-native language and identify a mispronunciation of the word in the utterance based on a comparison of the acoustic data with the acoustic model. The code causes the processor to send feedback related to the mispronunciation of the word to the language learner.