Abstract: In one aspect, a first device may include at least one processor, a touch-enabled display accessible to the at least one processor, and storage accessible to the at least one processor. The storage may include instructions executable by the at least one processor to facilitate, at the first device, a telephone call with a second device. The instructions may also be executable to, during facilitation of the telephone call, present a graphical user interface (GUI) on the touch-enabled display. The GUI may include a selector that is selectable to command the first device to audibly provide, from the first device to the second device, information as part of the telephone call. The instructions may also be executable to receive user input selecting the selector and to, responsive to receipt of the user input selecting the selector, audibly provide the information to the second device as part of the telephone call.

Abstract: Systems, methods, and devices for recognizing a user are disclosed. A speech-controlled device captures a spoken utterance, and sends audio data corresponding thereto to a server. The server determines content sources storing or having access to content responsive to the spoken utterance. The server also determines multiple users associated with a profile of the speech-controlled device. Using the audio data, the server may determine user recognition data with respect to each user indicated in the speech-controlled device's profile. The server may also receive user recognition confidence threshold data from each of the content sources. The server may determine user recognition data associated that satisfies (i.e., meets or exceeds) a most stringent (i.e., highest) of the user recognition confidence threshold data. Thereafter, the server may send data indicating a user associated with the user recognition data to all of the content sources.

Abstract: Systems and methods of determining phonetic relationships are provided. For instance data indicative of an input text phrase input by a user can be received. An audio output corresponding to a spoken rendering of the input text phrase can be determined. A text transcription of the audio output of the input text phrase can be determined. The text transcription can be a textual representation of the audio output. The text transcription can be compared against a plurality of test phrases to identify a match between the text transcription and at least one test phrase.

Abstract: A speech recognition method includes: obtaining speech information; and determining beginning and ending positions of a candidate speech segment in the speech information by using a weighted finite state transducer (WFST) network. The candidate speech segment is identified as corresponding to a preset keyword. The method also includes clipping the candidate speech segment from the speech information according to the beginning and ending positions of the candidate speech segment; detecting whether the candidate speech segment includes a preset keyword by using a machine learning model; and determining, upon determining that the candidate speech segment comprises the preset keyword, that the speech information comprises the preset keyword.

Abstract: Systems and techniques for automated voice assistant personality selector are described herein. A task may be identified that is to be completed by a user of a voice-enabled virtual assistant. A response may be output in connection with the task using a default personality for the voice-enabled virtual assistant selected based on the task. A task completion checkpoint may be determined for the task. It may be identified that the task completion checkpoint has not been reached. A personality profile of the user may be compared to personality data of a set of voice-enabled virtual assistant profiles corresponding to respective members of a set of available voice personalities for the voice-enabled virtual assistant. An escalation personality may be selected for the voice-enabled virtual assistant based the comparison and the task. Commands for facilitating user completion of the task may be transmitted via the voice-enabled virtual assistant using the selected escalation personality.

Abstract: A method for generating a bitstream indicative of an object based audio program is described. The bitstream comprises a sequence of containers. A first container of the sequence of containers comprises a plurality of substream entities for a plurality of substreams of the object based audio program and a presentation section. The method comprises determining a set of object channels. The method further comprises providing a set of object related metadata for the set of object channels. In addition, the method comprises inserting a first set of object channel frames and a first set of object related metadata frames into a respective set of substream entities of the first container. Furthermore, the method comprises inserting presentation data into the presentation section.

Abstract: An application automatically composed using natural language processing. A natural language input comprising one or more application requirements is received via an interface. The natural language input is parsed to extract one or more chunks, each chunk representing one of the application requirements, and at least one of the chunks representing at least one of one or more main functionalities described by the application requirements. A coarse architecture logically arranging the main functionalities to satisfy the application requirements is inferred according to the chunks. Existing assets corresponding to the chunks are identified, each asset associated with at least one of the main functionalities. The identified assets are assembled according to the coarse architecture. The assembled assets are deployed as an application.

Abstract: A method for identifying phrases in a text document having a similar discourse to a candidate phrase includes separating text in a document file into a plurality of phrases and generating a plurality of embedding vectors in a textual embedding space by inputting the plurality of phrases into an embedding engine. A mapping of each embedding vector in the textual embedding space is generated with each corresponding phrase and a document location of each corresponding phrase in the document file. A candidate phrase is received by a user and a candidate embedding vector is generated using the embedding engine. Similarity scores are computed based on the plurality of embedding space distances between the candidate phrase embedding vector location and each respective location of each embedding vector in the textual embedding space. A listing of phrases with the highest similarity scores are outputted with respective document locations in the text.

Abstract: An encouraging speech system performs an encouraging speech for encouraging an action of each user for each of a plurality of users. The encouraging speech system includes: state detection means for detecting states of the respective users; information acquisition means for acquiring information that relates to nursing care or medical care of the respective users; and encouraging speech means for associating the states of the respective users detected by the state detection means with the information that relates to the nursing care or the medical care of the respective users acquired by the information acquisition means and making the encouraging speech for each of the users so as to encourage interaction between the users.

Abstract: A speech synthesis method, a speech synthesis device, and an electronic apparatus are provided, which relate to a field of speech synthesis. Specific implementation solution is the following: inputting text information into an encoder of an acoustic model, to output a text feature of a current time step; splicing the text feature of the current time step with a spectral feature of a previous time step to obtain a spliced feature of the current time step, and inputting the spliced feature of the current time step into an decoder of the acoustic model to obtain a spectral feature of the current time step; and inputting the spectral feature of the current time step into a neural network vocoder, to output speech.

Abstract: A computer-implemented input-method editor process includes receiving a request from a user for an application-independent input method editor having written and spoken input capabilities, identifying that the user is about to provide spoken input to the application-independent input method editor, and receiving a spoken input from the user. The spoken input corresponds to input to an application and is converted to text that represents the spoken input. The text is provided as input to the application.

Abstract: An electronic device disclosed in the disclosure includes a display, a communication interface comprising communication circuitry, a processor, and a memory. The memory may be configured to store instructions which, when executed, cause the processor to control the electronic device to: determine whether an external device is outputting a voice response corresponding to an utterance input of a user, receive a specified user interaction, and allow visual information associated with the voice response to be displayed on the display in response to the user interaction.

Abstract: A method for phoneme identification. The method includes receiving an audio signal from a speaker, performing initial processing comprising filtering the audio signal to remove audio features, the initial processing resulting in a modified audio signal, transmitting the modified audio signal to a phoneme identification method and a phoneme replacement method to further process the modified audio signal, and transmitting the modified audio signal to a speaker. Also, a system for identifying and processing audio signals. The system includes at least one speaker, at least one microphone, and at least one processor, wherein the processor processes audio signals received using a method for phoneme replacement.

Abstract: The present application discloses a cross-media retrieval method based on deep semantic space, which includes a feature generation stage and a semantic space learning stage. In the feature generation stage, a CNN visual feature vector and an LSTM language description vector of an image are generated by simulating a perception process of a person for the image; and topic information about a text is explored by using an LDA topic model, thus extracting an LDA text topic vector. In the semantic space learning phase, a training set image is trained to obtain a four-layer Multi-Sensory Fusion Deep Neural Network, and a training set text is trained to obtain a three-layer text semantic network, respectively. Finally, a test image and a text are respectively mapped to an isomorphic semantic space by using two networks, so as to realize cross-media retrieval. The disclosed method can significantly improve the performance of cross-media retrieval.

Abstract: A method includes obtaining, by data processing hardware, a plurality of non-watermarked speech samples. Each non-watermarked speech does not include an audio watermark sample. The method includes, from each non-watermarked speech sample of the plurality of non-watermarked speech samples, generating one or more corresponding watermarked speech samples that each include at least one audio watermark. The method includes training, using the plurality of non-watermarked speech samples and corresponding watermarked speech samples, a model to determine whether a given audio data sample includes an audio watermark, and after training the model, transmitting the trained model to a user computing device.

Abstract: A method and an apparatus for synthesizing an audio signal are described. A spectral tilt is applied to the code of a codebook used for synthesizing a current frame of the audio signal. The spectral tilt is based on the spectral tilt of the current frame of the audio signal. Further, an audio decoder operating in accordance with the inventive approach is described.

Abstract: Aspects of the present disclosure relate to voice command filtering. Communication is established with a voice controlled device located at a location. Data indicating blocked directions is received from the voice controlled device. A voice command is received. A determination is made that the voice command is received from a blocked direction indicated in the data. The received voice command is then ignored.

Abstract: A method of controlling a battery-powered remote controller to decrease a duty cycle to allow continued operations despite the quantity of the battery is bad determines a drop in voltage of the battery in standby mode as voltage of the battery is being read. When receiving a command to activate a voice function, determining whether the drop in voltage in standby mode is greater than or equal to a preset value. If yes, the method then determines whether the drop in voltage falls in a preset range. If yes, the method regulates a duty cycle of the pulse signal activating the voice function, and activates the voice function as required. A remote controller and a non-transitory storage medium are also provided.

Abstract: An electronic device may capture a voice command from a user. The electronic device may store contextual information about the state of the electronic device when the voice command is received. The electronic device may transmit the voice command and the contextual information to computing equipment such as a desktop computer or a remote server. The computing equipment may perform a speech recognition operation on the voice command and may process the contextual information. The computing equipment may respond to the voice command. The computing equipment may also transmit information to the electronic device that allows the electronic device to respond to the voice command.

Abstract: Disclosed herein are an artificial intelligence apparatus and a method of operating the same. The artificial intelligence apparatus includes one or more processors that obtain weight data of a container and speech data, determines whether the container is seated on a seating portion of a water dispensing apparatus using the weight data, adjusts a speech recognition sensitivity according to whether the container is seated on the seating portion, inputs the first speech data to a speech recognition model and allows the water dispensing apparatus to perform a first water dispensing operation corresponding to first water dispensing information when the speech recognition model outputs the first water dispensing information based on the first speech data.