Transferring (e.g., automatically) an automated assistant routine between client devices during execution of the automated assistant routine. The automated assistant routine can correspond to a set of actions to be performed by one or more agents and/or one or more devices. While content, corresponding to an action of the routine, is being rendered at a particular device, the user may walk away from the particular device and toward a separate device. The automated assistant routine can be automatically transferred in response, and the separate device can continue to rendering the content for the user.

Implementations are set forth herein for creating an order of execution for actions that were requested by a user, via a spoken utterance to an automated assistant. The order of execution for the requested actions can be based on how each requested action can, or is predicted to, affect other requested actions. In some implementations, an order of execution for a series of actions can be determined based on an output of a machine learning model, such as a model that has been trained according to supervised learning. A particular order of execution can be selected to mitigate waste of processing, memory, and network resources—at least relative to other possible orders of execution. Using interaction data that characterizes past performances of automated assistants, certain orders of execution can be adapted over time, thereby allowing the automated assistant to learn from past interactions with one or more users.

Provided are a speech recognition method and system, and a storage medium. The speech recognition method includes: receiving a feature vector and a decoding map sent by a CPU, wherein the feature vector is extracted from a speech signal, and the decoding map is pre-trained; recognizing the feature vector according to a pre-trained acoustic model to obtain a probability matrix; decoding the probability matrix according to the decoding map using a parallel mechanism to obtain text sequence information; and sending the text sequence information to the CPU.

Provided are a speech recognition method and system, and a storage medium. The speech recognition method includes: receiving a feature vector and a decoding map sent by a CPU, wherein the feature vector is extracted from a speech signal, and the decoding map is pre-trained; recognizing the feature vector according to a pre-trained acoustic model to obtain a probability matrix; decoding the probability matrix according to the decoding map using a parallel mechanism to obtain text sequence information; and sending the text sequence information to the CPU.

A speech interface device is configured with “hybrid” capabilities, which allows the speech interface device to perform actions in response to user speech, even when the speech interface device is unable to communicate with a remote system over a wide area network (e.g., the Internet). A hybrid request selector of the speech interface device sends audio data representing user speech to both a remote speech processing system and a local speech processing component executing on the speech interface device, and then waits for a response from either or both components. The local speech processing component may start execution based on the audio data and subsequently suspend the execution until further instruction from the hybrid request selector. The hybrid request selector can then determine which response to use, and, depending on which response is chosen, may instruct the local speech processing component to either continue or terminate the suspended execution.

A speech interface device is configured with “hybrid” capabilities, which allows the speech interface device to perform actions in response to user speech, even when the speech interface device is unable to communicate with a remote system over a wide area network (e.g., the Internet). A hybrid request selector of the speech interface device sends audio data representing user speech to both a remote speech processing system and a local speech processing component executing on the speech interface device, and then waits for a response from either or both components. The local speech processing component may start execution based on the audio data and subsequently suspend the execution until further instruction from the hybrid request selector. The hybrid request selector can then determine which response to use, and, depending on which response is chosen, may instruct the local speech processing component to either continue or terminate the suspended execution.

Disclosed is a dialogue processing system using speech act control, the dialogue processing system comprising: a main speech act unit which processes a free speech act and performs speech act control such that the free speech act returns to a main speech act, thereby processing a multi-turn dialogue in a consistent manner, and which processes a purposed utterance having a set purpose, for reaching a final dialogue objective; and a free speech act unit which processes a free utterance deviating from the purposed utterance and performs control such that the free utterance returns to the main speech act unit by searching for a node capable of returning to the purposed utterance.

Disclosed is a dialogue processing system using speech act control, the dialogue processing system comprising: a main speech act unit which processes a free speech act and performs speech act control such that the free speech act returns to a main speech act, thereby processing a multi-turn dialogue in a consistent manner, and which processes a purposed utterance having a set purpose, for reaching a final dialogue objective; and a free speech act unit which processes a free utterance deviating from the purposed utterance and performs control such that the free utterance returns to the main speech act unit by searching for a node capable of returning to the purposed utterance.

Disclosed are a virtual reality device control method and apparatus, and a virtual reality device and system. The method comprises: acquiring a voice signal; performing local speech recognition on the voice signal; if a local speech recognition library cannot recognize the voice signal, sending the voice signal to a cloud management server to perform speech recognition; and receiving an operation instruction, sent by the cloud management server, obtained after the voice signal is recognized, executing the operation instruction, and acquiring a resource matching the operation instruction from the Internet.

Disclosed are a virtual reality device control method and apparatus, and a virtual reality device and system. The method comprises: acquiring a voice signal; performing local speech recognition on the voice signal; if a local speech recognition library cannot recognize the voice signal, sending the voice signal to a cloud management server to perform speech recognition; and receiving an operation instruction, sent by the cloud management server, obtained after the voice signal is recognized, executing the operation instruction, and acquiring a resource matching the operation instruction from the Internet.