Abstract: A smart home interaction system is presented. It is built on a multi-modal, multithreaded conversational dialog engine. The system provides a natural language user interface for the control of household devices, appliances or household functionality. The smart home automation agent can receive input from users through sensing devices such as a smart phone, a tablet computer or a laptop computer. Users interact with the system from within the household or from remote locations. The smart home system can receive input from sensors or any other machines with which it is interfaced. The system employs interaction guide rules for processing reaction to both user and sensor input and driving the conversational interactions that result from such input. The system adaptively learns based on both user and sensor input and can learn the preferences and practices of its users.

Abstract: A system and method for parallel speech recognition processing of multiple audio signals produced by multiple microphones in a handheld portable electronic device. In one embodiment, a primary processor transitions to a power-saving mode while an auxiliary processor remains active. The auxiliary processor then monitors the speech of a user of the device to detect a wake-up command by speech recognition processing the audio signals in parallel. When the auxiliary processor detects the command it then signals the primary processor to transition to active mode. The auxiliary processor may also identify to the primary processor which microphone resulted in the command being recognized with the highest confidence. Other embodiments are also described.

Abstract: The invention is directed to combining web browser and audio player functionality for the organization and consumption of web documents. Specifically, the invention identifies a set of web documents via a web browser, extracts content from the web documents, and adds the set of web documents to a playlist. In this way, users can build a playlist of web documents and utilize the functionality and convenience of an audio player and listen to the content of the playlist.

Abstract: An aspect provides a method, including: playing, on a display device, video content; providing, using at least one speaker, audio content associated with the video content; obtaining, from an external source, data relating to playback context; determining, using a processor, that the data relating to playback context is associated with a reduced audibility context; and providing, on the display device, textual data associated with dialog of the video content. Other aspects are described and claimed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for classification using neural networks. One method includes receiving audio data corresponding to an utterance. Obtaining a transcription of the utterance. Generating a representation of the audio data. Generating a representation of the transcription of the utterance. Providing (i) the representation of the audio data and (ii) the representation of the transcription of the utterance to a classifier that, based on a given representation of the audio data and a given representation of the transcription of the utterance, is trained to output an indication of whether the utterance associated with the given representation is likely directed to an automated assistance or is likely not directed to an automated assistant.

Abstract: An approach is provided in which an information handling system sends a request in audio format to a user over a voice channel requesting a user data set. The information handling system receives utterances from the user over the voice channel and determines that the utterances do not provide enough information to complete the requested user data set. In turn, the information handling system establishes a messaging channel with the user and sends a request in digital format to the user over the messaging channel to provide additional data to complete the user data set.

Abstract: A system capable of performing natural language understanding (NLU) without the concept of a domain that influences NLU results. The present system uses a hierarchical organizations of intents/commands and entity types, and trained models associated with those hierarchies, so that commands and entity types may be determined for incoming text queries without necessarily determining a domain for the incoming text. The system thus operates in a domain agnostic manner, in a departure from multi-domain architecture NLU processing where a system determines NLU results for multiple domains simultaneously and then ranks them to determine which to select as the result.

Abstract: A method and an apparatus for determining a morpheme importance analysis model is provided, which belongs to the field of computers. The method includes: acquiring at least two pieces of training data, each piece of training data including a query, any morpheme in the query, and an importance score of the any morpheme in the query; determining a feature value of each preset feature of each piece of training data; and determining a model parameter according to the feature value of each preset feature of all training data and importance scores of morphemes included in all training data, and determining a morpheme importance analysis model according to the determined model parameter.

Abstract: According to one embodiment, a method, computer system, and computer program product for natural language processing is provided. The present invention may include detecting natural language entities, and running parsing algorithms on the natural language entities to determine the relationship between said natural language entities. The present invention may further comprise assigning, by the parsing algorithms, initial scores to detected natural language entities based on the relationship between said natural language entities; choosing a final score for plurality of natural language entities; and comparing the final score against a threshold to determine whether the natural language entities are within the same context.

Abstract: A voice interactive device that interacts with a user by voice, the device comprises a voice input unit that acquires and recognizes voice uttered by a user; a degree-of-intimacy calculating unit that calculates a degree of intimacy with the user; a response generating unit that generates a response to the recognized voice, based on the degree of intimacy; and a voice output unit that outputs the response by voice, wherein the degree-of-intimacy calculating unit calculates a degree of intimacy with the user based on a sum of a first intimacy value calculated based on a content of an utterance made by the user and a second intimacy value calculated, based on the number of previous interactions with the user.

Abstract: A device including a speech recognition function which recognizes speech from a user, includes: a loudspeaker which outputs speech to a space; a microphone which collects speech in the space; a first speech recognition unit which recognizes the speech collected by the microphone; a command control unit which issues a command for controlling the device, based on the speech recognized by the first speech recognition unit; and a control unit which prohibits the command issuance unit from issuing the command, based on the speech to be output from the loudspeaker.

Abstract: A system for enhancement of noisy speech comprises an input unit is configured to subdivide the spectrum of the input signal into a plurality of frequency sub-bands and to provide time-frequency coefficients X(k,m) for a sequence [X(k,m??D+1) . . . X(k,m?)] of observable noisy signal samples for each of said frequency sub-bands, where k and m are frequency and time indices, respectively, and D is larger than 1. The system further comprises enhancement processing unit configured to receive X(k,m) and to provide enhanced time-frequency coefficients ?(k,m), a storage for statistical model(s) of speech and for statistical model(s) of noise, and an optimizing unit configured to provide said enhanced time-frequency coefficients ?(k,m) using said statistical model of speech and said statistical model of noise, while considering said sequence [X(k,m??D+1) . . . X(k,m?)] of observable noisy signal samples.

Abstract: Examples for augmenting user recognition via speech are provided. One example method comprises, on a computing device, monitoring a use environment via one or more sensors including an acoustic sensor, detecting utterance of a key phrase via data from the acoustic sensor, and based upon the selected data from the acoustic sensor and also on other environmental sensor data collected at different times than the selected data from the acoustic sensor, determining a probability that the key phrase was spoken by an identified user. The method further includes, if the probability meets or exceeds a threshold probability, then performing an action on the computing device.

Abstract: A method, a device, and a non-transitory storage medium are described in which a power of late reverberation of a speech signal is estimated based on early samples of the speech signal. The power of the late reverberation may be subtracted linearly or non-linearly from the speech signal.

Abstract: A computing device may compare a voice command to a customized voiceprint of a user. The computing device may, if a result of the comparison exceeds a threshold, determine the voice command matches the voiceprint, determine a security level associated with the voice command, generate a signal comprising an audible announcement, access website related information, and utilize customized user settings.

Abstract: An apparatus for processing an audio signal including a sequence of blocks of spectral values, includes: a processor for calculating an aliasing-affected signal using at least one first modification value for a first block of the sequence of blocks and using at least one different second modification value for a second block of the sequence of blocks and for estimating an aliasing-error signal representing an aliasing-error in the aliasing-affected signal; and a combiner for combining the aliasing-affected signal and the aliasing-error signal such that a processed signal obtained by the combining is an aliasing-reduced or aliasing-free signal.

Abstract: The application relates to a terminal and method for voice control on a terminal. A terminal according to some embodiments of the application includes: one or more processors, and a memory, wherein, the memory stores therein one or more computer readable program codes, and the processor or processors are configured to execute the one or more computer readable program codes, to match voice information in a voice instruction with preset voice information in the terminal upon reception of the voice instruction comprising the voice information and instruction information, to perform an operation corresponding to the instruction information upon determining successful matching, and to reject the operation corresponding to the instruction information upon determining unsuccessful matching.

Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.

Abstract: An improved gain-shape vector quantization is achieved by determining a number of bits to be allocated to a gain adjustment- and shape-quantizer for a plurality of combinations of a current bit rate and a first signal property. The bit allocation is derived by using an average of optimal bit allocations for a training data set. A number of bits to the gain adjustment and the shape quantizers for a plurality of combinations of the bit rate and a first signal are pre-calculated, and a table indicating the number of bits to be allocated to the gain adjustment- and the shape-quantizers for a plurality of combinations of the bit rate and a first signal property is created. In this way, the table can be used for achieving an improved bit allocation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for designating certain voice commands as hotwords. The methods, systems, and apparatus include actions of receiving a hotword followed by a voice command. Additional actions include determining that the voice command satisfies one or more predetermined criteria associated with designating the voice command as a hotword, where a voice command that is designated as a hotword is treated as a voice input regardless of whether the voice command is preceded by another hotword. Further actions include, in response to determining that the voice command satisfies one or more predetermined criteria associated with designating the voice command as a hotword, designating the voice command as a hotword.