A system can operate a speech-controlled device in a mode where the speech-controlled device determines that an utterance is directed at the speech-controlled device using image data showing the user speaking the utterance. If the user is directing the user's gaze at the speech-controlled device while speaking, the system may determine the utterance is system directed and thus may perform further speech processing based on the utterance. If the user's gaze is directed elsewhere, the system may determine the utterance is not system directed (for example directed at another user) and thus the system may not perform further speech processing based on the utterance and may take other actions, for example discarding audio data of the utterance.

A natural language system may be configured to act as a participant in a conversation between two users. The system may determine when a user expression such as speech, a gesture, or the like is directed from one user to the other. The system may processing input data related the expression (such as audio data, input data, language processing result data, conversation context data, etc.) to determine if the system should interject a response to the user-to-user expression. If so, the system may process the input data to determine a response and output it. The system may track that response as part of the data related to the ongoing conversation.

A system that is capable of resolving anaphora using timing data received by a local device. A local device outputs audio representing a list of entries. The audio may represent synthesized speech of the list of entries. A user can interrupt the device to select an entry in the list, such as by saying “that one.” The local device can determine an offset time representing the time between when audio playback began and when the user interrupted. The local device sends the offset time and audio data representing the utterance to a speech processing system which can then use the offset time and stored data to identify which entry on the list was most recently output by the local device when the user interrupted. The system can then resolve anaphora to match that entry and can perform additional processing based on the referred to item.

Described herein is a system for enabling a user to multitask by allowing a user to pause or interrupt an on-going interaction with a skill. The system monitors a state of a skill session, and updates the state to allow the user or system to suspend the session. The user may provide an instruction to pause an active session, causing the system to place the session in a suspended state. The user may then provide an instruction to resume the suspended session, causing the system to place the session in an active state. In other cases, the user input may be a request during an active session that requires invoking another skill. The system may place the current session in a suspended state, and invoke a second skill session to monitor the interaction with a second skill. When the interaction with the second skill is completed, the system may resume the previous session by placing it in an active state.

An example method includes, at an electronic device: receiving an indication of a notification; in accordance with receiving the indication of the notification: obtaining one or more data streams from one or more sensors; determining, based on the one or more data streams, whether a user associated with the electronic device is speaking; and in accordance with a determination that the user is not speaking: causing an output associated with the notification to be provided.

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 for an automated calling system are disclosed. Some implementations are directed to using a bot to initiate telephone calls and conduct telephone conversations with a user. The bot may be interrupted while providing synthesized speech during the telephone call. The interruption can be classified into one of multiple disparate interruption types, and the bot can react to the interruption based on the interruption type. Some implementations are directed to determining that a first user is placed on hold by a second user during a telephone conversation, and maintaining the telephone call in an active state in response to determining the first user hung up the telephone call. The first user can be notified when the second user rejoins the call, and a bot associated with the first user can notify the first user that the second user has rejoined the telephone call.

The technology described in this document can be embodied in a computer-implemented method that includes receiving, at a processing system, a first signal including an output of a speaker device and an additional audio signal. The method also includes determining, by the processing system, based at least in part on a model trained to identify the output of the speaker device, that the additional audio signal corresponds to an utterance of a user. The method further includes initiating a reduction in an audio output level of the speaker device based on determining that the additional audio signal corresponds to the utterance of the user.

Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.

Systems and methods are provided for improving audio processing by receiving an external input sound message during playing a first audio message; matching the external input sound message with a receiving message to obtain a matching result, wherein the receiving message is associated with the first audio message in content, wherein the matching is based on a proportion of sound units in the sound message that hit sound units in the receiving message; determining whether the matching result meets a threshold; and upon determining that the matching result meets the threshold, stop playing the first audio message.