Abstract: There is presented mechanisms for handling input envelope representation coefficients. A method is performed by an encoder of a communication system. The method comprises determining envelope representation residual coefficients as first compressed envelope representation coefficients subtracted from the input envelope representation coefficients. The method comprises transforming the envelope representation residual coefficients into a warped domain so as to obtain transformed envelope representation residual coefficients. The method comprises applying, at least one of a plurality of gain-shape coding schemes on the transformed envelope representation residual coefficients in order to achieve gain-shape coded envelope representation residual coefficients, where the plurality of gain-shape coding schemes have mutually different trade-offs in one or more of gain resolution and shape resolution for one or more of the transformed envelope representation residual coefficients.

Abstract: In general, the subject matter described in this specification can be embodied in methods, systems, and program products for receiving a voice query at a mobile computing device and generating data that represents content of the voice query. The data is provided to a server system. A textual query that has been determined by a speech recognizer at the server system to be a textual form of at least part of the data is received at the mobile computing device. The textual query is determined to include a carrier phrase of one or more words that is reserved by a first third-party application program installed on the computing device. The first third-party application is selected, from a group of one or more third-party applications, to receive all or a part of the textual query. All or a part of the textual query is provided to the selected first application program.

Abstract: Processing stacked data structures is provided. A system receives an input audio signal detected by a sensor of a local computing device, identifies an acoustic signature, and identifies an account corresponding to the signature. The system establishes a session and a profile stack data structure including a first profile layer having policies configured by a third-party device. The system pushes, to the profile stack data structure, a second profile layer retrieved from the account. The system parses the input audio signal to identify a request and a trigger keyword. The system generates, based on the trigger keyword and the second profile layer, a first action data structure compatible with the first profile layer. The system provides the first action data structure for execution. The system disassembles the profile stack data structure to remove the first profile layer or the second profile layer from the profile stack data structure.

Abstract: Tools are provided to allow developers to enable applications for Conversational Understanding (CU) using assets from a CU service. The tools may be used to select functionality from existing domains, extend the coverage of one or more domains, as well as to create new domains in the CU service. A developer may provide example Natural Language (NL) sentences that are analyzed by the tools to assist the developer in labeling data that is used to update the models in the CU service. For example, the tools may assist a developer in identifying domains, determining intent actions, determining intent objects and determining slots from example NL sentences. After the developer tags all or a portion of the example NL sentences, the models in the CU service are automatically updated and validated. For example, validation tools may be used to determine an accuracy of the model against test data.

Abstract: A dialogue complexity assessment method, system, and computer program product for introducing the notion of dialogue complexity to understand and compare dialogues in a repository, calculating the dialogue complexity, use the dialogue complexity to understand customer interactions in a variety of domains using public and proprietary data, and demonstrate the dialogue complexity usage to improve a service management operation.

Abstract: A system and method for detecting speech from occupants in a building management system is disclosed. Building management systems include fire alarm systems, building automation systems and security systems, in examples. Installed devices deployed within the building include audio transducers that detect speech from the occupants, and a management system panel processes the information from the installed devices and processes the detected speech from the occupants. In a fire alarm system, in one example, the fire alarm panel processes the detected speech from fire sensor devices and alarm notification devices as the installed devices. The fire alarm panel and/or its installed devices can identify commands from the detected speech for controlling and testing the fire alarm management system. In embodiments, Artificial Intelligence (AI) subsystems can be further added to the building management systems for control and information services.

Abstract: Provide automatic assessment of oral recitations during computer based language assessments using a trained neural network to automate the scoring and feedback processes without human transcription and scoring input by automatically generating a score of a language assessment. Providing an automatic speech recognition (“ASR”) scoring system. Training multiple scoring reference vectors associated with multiple possible scores of an assessment, and receiving an acoustic language assessment response to an assessment item. Based on the acoustic language assessment automatically generating a transcription, and generating an individual word vector from the transcription. Generating an input vector by concatenating an individual word vector with a transcription feature vector, and supplying an input vector as input to a neural network. Generating an output vector based on weights of a neural network; and generating a score by comparing an output vector with scoring vectors.

Abstract: Systems and methods are disclosed configured to detect impairment issues, and via an interlock device, inhibit operation of an item of equipment when impairment is detected. The interlock device may comprise a solid state relay, an electromechanical relay, and/or a solenoid. The interlock device may perform power isolation and/or may use a mechanism, such as a rotating cam or gear, to immobilize a control and/or other components. Based on detected impairment, a determination is made as to whether the interlock is to be activated or deactivated.

Abstract: A computer-implemented conversational agent engages in a natural language conversation with a user, interpreting the natural language conversation by parsing and tokenizing utterances in the natural language conversation. Based on interpreting, a set of utterances in the natural language conversation to be recorded as a macro is determined. The macro is stored in a database with an associated macro identifier. Replaying of the macro executes a function specified in the set of utterances.

Abstract: An offline semantic processor of a resource-constrained voice-enabled device such as a mobile device utilizes an offline grammar model with reduced resource requirements to parse voice-based queries received by the device. The offline grammar model may be generated from a larger and more comprehensive grammar model used by an online voice-based query processor, and the generation of the offline grammar model may be based upon query usage data collected from one or more users to enable a subset of more popular voice-based queries from the online grammar model to be incorporated into the offline grammar model. In addition, such a device may collect query usage data and upload such data to an online service to enable an updated offline grammar model to be generated and downloaded back to the device and thereby enable a dynamic update of the offline grammar model to be performed.

Abstract: Methods, systems, and vehicle components for providing a corrected pronunciation suggestion to a user are disclosed. A method includes receiving, by a microphone communicatively coupled to a processing device, a voice input from the user, the voice input including a particularly pronounced word. The method further includes comparing, by the processing device, the particularly pronounced word to one or more reference words in a reference table, determining, by the processing device, that the particularly pronounced word has been potentially mispronounced by the user based on the one or more reference words in the reference table, determining, by the processing device, a corrected pronunciation suggestion from the one or more reference words, and providing, via a user interface, the corrected pronunciation suggestion to the user.

Abstract: Audio signal processing enhances audio watermark embedding and detecting processes. Audio signal processes include audio classification and adapting watermark embedding and detecting based on classification. Advances in audio watermark design include adaptive watermark signal structure data protocols, perceptual models, and insertion methods. Perceptual and robustness evaluation is integrated into audio watermark embedding to optimize audio quality relative the original signal, and to optimize robustness or data capacity. These methods are applied to audio segments in audio embedder and detector configurations to support real time operation. Feature extraction and matching are also used to adapt audio watermark embedding and detecting.

Abstract: An apparatus and a method to encode and decode a speech signal using an encoding mode are provided. An encoding apparatus may select an encoding mode of a frame included in an input speech signal, and encode a frame having an unvoiced mode for an unvoiced speech as the selected encoding mode.

Abstract: Technology is described for removing sensitive information. An audio block that represents a portion of a conversation may be identified. A text representation for the audio block may be obtained using a speech-to-text process. The text representation for the audio block may be compared to pattern rules to mark sensitive information in the audio block. A portion of audio data from the audio block marked as sensitive information may be removed in the audio block.

Abstract: A user speech interface for interactive media guidance applications, such as television program guides, guides for audio services, guides for video-on-demand (VOD) services, guides for personal video recorders (PVRs), or other suitable guidance applications is provided. Voice commands may be received from a user and guidance activities may be performed in response to the voice commands.

Abstract: A system and method for segmenting an audio file. The method includes analyzing an audio file, wherein the analyzing includes identifying speech recognition features within the audio file; generating metadata based on the audio file, wherein the metadata includes transcription characteristics of the audio file; and determining a segmenting interval for the audio file based on the speech recognition features and the metadata.

Abstract: An offline semantic processor of a resource-constrained voice-enabled device such as a mobile device utilizes an offline grammar model with reduced resource requirements to parse voice-based queries received by the device. The offline grammar model may be generated from a larger and more comprehensive grammar model used by an online voice-based query processor, and the generation of the offline grammar model may be based upon query usage data collected from one or more users to enable a subset of more popular voice-based queries from the online grammar model to be incorporated into the offline grammar model. In addition, such a device may collect query usage data and upload such data to an online service to enable an updated offline grammar model to be generated and downloaded back to the device and thereby enable a dynamic update of the offline grammar model to be performed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for neural network adaptive beamforming for multichannel speech recognition are disclosed. In one aspect, a method includes the actions of receiving a first channel of audio data corresponding to an utterance and a second channel of audio data corresponding to the utterance. The actions further include generating a first set of filter parameters for a first filter based on the first channel of audio data and the second channel of audio data and a second set of filter parameters for a second filter based on the first channel of audio data and the second channel of audio data. The actions further include generating a single combined channel of audio data. The actions further include inputting the audio data to a neural network. The actions further include providing a transcription for the utterance.

Abstract: A computer readable medium containing a set of instructions that causes a computer to perform a process comprised of receiving one or more media files. The one or more media files having one or more scenes and each scene including a starting time point and ending time point. The set of instructions may include changing the starting time point and/or the ending time point of a scene from the one or more scenes in response to an input command. The set of instructions may create a new scene and save the new scene based on the new starting time point and/or ending time point of the scene.

Abstract: A voice encoder/decoder (vocoder) may provide receiving a voice sample and generating zero crossings of the voice sample in response to voice excitation in a first formant and creating a corresponding output signal. Additional operations may include dividing the output signal by two, and sampling the output signal at a predefined frequency such that a resulting combination uses half of a bit rate for an excitation and a remainder for short term spectrum analysis.