Techniques are disclosed that enable automating user interface input by generating a sequence of actions to perform a task utilizing a multi-agent reinforcement learning framework. Various implementations process an intent associated with received user interface input using a holistic reinforcement policy network to select a software reinforcement learning policy network. The sequence of actions can be generated by processing the intent, as well as a sequence of software client state data, using the selected software reinforcement learning policy network. The sequence of actions are utilized to control the software client corresponding to the selected software reinforcement learning policy network.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, relating to synthetic call status updates. In some implementations, a method includes determining, by a task manager module, that a triggering event has occurred to provide a current status of a user call request. The method may then determine, by the task manager module, the current status of the user call request. A representation of the current status of the user call request is generated. Then, the generated representation of the current status of the user call request is provided to the user.

[Object] The technology that can improve accuracy of speech recognition for collected sound data is provided. [Solution] Provided is an information processing device including: a collected sound data acquisition portion that acquires collected sound data; and an output controller that causes an output portion to output at least whether or not a state of the collected sound data is suitable for speech recognition.

A computer speech output control method, system, and non-transitory computer readable medium, include a computer speech output control system, including a computer speech output unit configured to output a computer speech, a human speech monitoring circuit configured to determine whether a human conversation is occurring, an interruption priority setting circuit configured to set a priority setting for when the human conversation can be interrupted by the computer speech, and an interruption determining circuit configured to determine whether to cause the computer speech output unit to output the computer speech based on the priority setting and a status of the human conversation.

Methods, apparatus, systems, and computer-readable media are provided for storing incomplete dialog sessions between a user and an automated assistant in order that the dialog sessions can be completed in furtherance of certain actions. While interacting with an automated assistant, a user can become distracted and not complete the interaction to the point of the automated assistant performing some action. In response, the automated assistant can store the interaction as a dialog session. Subsequently, the user may express interest, directly or indirectly, in completing the dialog session, and the automated assistant can provide the user with a selectable element that, when selected, causes the dialog session to be reopened. The user can then continue the dialog session with the automated assistant in order that the originally intended action can be performed by the automated assistant.

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.

A method of disambiguating user queries in a multi-turn dialogue including a set of user utterances. The method includes using a predefined language model to recognize an ambiguous entity in an unresolved user utterance from the multi-turn dialogue, and using the predefined language model to recognize entity constraints of the ambiguous entity. The method further includes, in a computer-accessible conversation history of the multi-turn dialogue, searching a set of previously-resolved entities for a candidate entity having entity properties with a highest confidence correspondence to the entity constraints of the ambiguous entity. The unresolved user utterance is rewritten as a rewritten utterance that replaces the ambiguous entity with the candidate entity. The rewritten utterance is output to one or more query answering machines.

Methods and systems are provided for processing speech for an autonomous or semi-autonomous vehicle. In one embodiment, a method includes receiving, by a processor, context data generated by the vehicle; determining, by a processor, a dialog delivery method based on the context data; and selectively generating, by a processor, a dialog prompt to the user via at least one output device based on the dialog delivery method.

A voice output is produced by a speech dialogue device between the acquisitions of two pieces of information. Each piece of information is acquired by acquiring natural verbal voice input data and extracting the respective piece of information from the voice input data using a speech recognition algorithm. When a repetition condition has been satisfied, a natural speech summary output is generated by the speech dialogue device and output as a voice output which includes a natural voice reproduction of at least one previously acquired piece of information or a part of this piece of information or a piece of information derived from this piece of information.

An information processing device is provided. The information processing device includes an output control unit that controls output of a spoken utterance related to information presentation. The output control unit outputs the spoken utterance, and visually displays an output position of an important part of the spoken utterance. In addition, an information processing method is provided. The information processing method includes controlling, by a processor, output of a spoken utterance related to information presentation. The controlling further includes outputting the spoken utterance and visually displaying an output position of an important part of the spoken utterance.