Abstract: Techniques for creating a persistent connection between client devices and one or more remote computing resources, which may form a portion of a network-accessible computing platform. This connection may be considered “permanent” or “nearly permanent” to allow the client device to both send data to and receive data from the remote resources at nearly any time. In addition, both the client device and the remote resources may establish virtual channels over this single connection. If no data is exchanged between the client device and the remote computing resources for a threshold amount of time, then the connection may be severed and the client device may attempt to establish a new connection with the remote computing resources.

Abstract: An open framework for computing devices to dispatch voice-based interactions to supporting applications. Applications are selected on a trial-and-error basis to find an application able to handle the voice interaction. Dispatching to the applications may be performed without a determination of meaning conveyed in the interaction, with meaning determined by the individual applications. Once an application acts upon a voice interaction, that application may be given first-right-of-refusal for subsequent voice interactions.

Abstract: Techniques for creating a persistent connection between client devices and one or more remote computing resources, which may form a portion of a network-accessible computing platform. This connection may be considered “permanent” or “nearly permanent” to allow the client device to both send data to and receive data from the remote resources at nearly any time. In addition, both the client device and the remote resources may establish virtual channels over this single connection. If no data is exchanged between the client device and the remote computing resources for a threshold amount of time, then the connection may be severed and the client device may attempt to establish a new connection with the remote computing resources.

Abstract: A system enables end user devices to receive audio announcements from third party cloud-based resources. For example, the system may include a first party cloud-based resource providing tokens to the third party cloud-based resource in order to prevent the third party cloud-based resource from causing audio announcements to be output by user devices without authorization. In some cases, the tokens may be time based and prevent the third party cloud-based resource from causing audio announcements to be output by user devices after a predefined amount of time. In other examples, the tokens may be use based and prevent the third party cloud-based resource from causing the user device to output more than a predetermined number of audio announcements.

Abstract: A speech-based system includes an audio device in a user premises and a network-based service that supports use of the audio device by multiple applications. The audio device may be directed to play audio content such as music, audio books, etc. The audio device may also be directed to interact with a user through speech. The network-based service monitors event messages received from the audio device to determine which of the multiple applications currently has speech focus. When receiving speech from a user, the service first offers the corresponding meaning to the application, if any, that currently has primary speech focus. If there is no application that currently has primary speech focus, or if the application having primary speech focus is not able to respond to the meaning, the service then offers the user meaning to the application that currently has secondary speech focus.

Abstract: A speech recognition platform configured to receive an audio signal that includes speech from a user and perform automatic speech recognition (ASR) on the audio signal to identify ASR results. The platform may identify: (i) a domain of a voice command within the speech based on the ASR results and based on context information associated with the speech or the user, and (ii) an intent of the voice command. In response to identifying the intent, the platform may perform a corresponding action, such as streaming audio to the device, setting a reminder for the user, purchasing an item on behalf of the user, making a reservation for the user or launching an application for the user. The speech recognition platform, in combination with the device, may therefore facilitate efficient interactions between the user and a voice-controlled device.

Abstract: A speech-based system includes an audio device in a user premises and a network-based service that supports use of the audio device by multiple applications. The audio device may be directed to play audio content such as music, audio books, etc. The audio device may also be directed to interact with a user through speech. The network-based service monitors event messages received from the audio device to determine which of the multiple applications currently has speech focus. When receiving speech from a user, the service first offers the corresponding meaning to the application, if any, that currently has primary speech focus. If there is no application that currently has primary speech focus, or if the application having primary speech focus is not able to respond to the meaning, the service then offers the user meaning to the application that currently has secondary speech focus.

Abstract: A speech recognition platform configured to receive an audio signal that includes speech from a user and perform automatic speech recognition (ASR) on the audio signal to identify ASR results. The platform may identify: (i) a domain of a voice command within the speech based on the ASR results and based on context information associated with the speech or the user, and (ii) an intent of the voice command. In response to identifying the intent, the platform may perform a corresponding action, such as streaming audio to the device, setting a reminder for the user, purchasing an item on behalf of the user, making a reservation for the user or launching an application for the user. The speech recognition platform, in combination with the device, may therefore facilitate efficient interactions between the user and a voice-controlled device.

Abstract: Network-based services may be provided to a user through the user of a speech-based user device located within a user environment. The speech-based user device may accept speech commands from a user and may also interact with the user by means of generated speech. Operating state of the speech-based user device may be provided to the network-based service and stored by the service. Applications that provide services through the speech-based interface may request and obtain the stored state information.

Abstract: A computing system for selecting and providing content items to a device. The device is configured to output a first content item to a user and to detect events related to the output of the first content item and, in response, to provide a notification to a cloud service related to the event. The device is further configured to receive at least a second content item from the cloud services and to buffer the second content item while outputting the first content item.

Abstract: Features are disclosed for generating markers for elements or other portions of an audio presentation so that a speech processing system may determine which portion of the audio presentation a user utterance refers to. For example, an utterance may include a pronoun with no explicit antecedent. The marker may be used to associate the utterance with the corresponding content portion for processing. The markers can be provided to a client device with a text-to-speech (“TTS”) presentation. The markers may then be provided to a speech processing system along with a user utterance captured by the client device. The speech processing system, which may include automatic speech recognition (“ASR”) modules and/or natural language understanding (“NLU”) modules, can generate hints based on the marker. The hints can be provided to the ASR and/or NLU modules in order to aid in processing the meaning or intent of a user utterance.

Abstract: Features are disclosed for generating markers for elements or other portions of an audio presentation so that a speech processing system may determine which portion of the audio presentation a user utterance refers to. For example, an utterance may include a pronoun with no explicit antecedent. The marker may be used to associate the utterance with the corresponding content portion for processing. The markers can be provided to a client device with a text-to-speech (“TTS”) presentation. The markers may then be provided to a speech processing system along with a user utterance captured by the client device. The speech processing system, which may include automatic speech recognition (“ASR”) modules and/or natural language understanding (“NLU”) modules, can generate hints based on the marker. The hints can be provided to the ASR and/or NLU modules in order to aid in processing the meaning or intent of a user utterance.

Abstract: A speech-based system includes a local device in a user premises and a remote service that uses the local device to conduct speech dialogs with a user. The local device may also be directed to play audio such as music, audio books, etc. When designating audio for playing by the local device, the remote service may specify that the audio is either background audio or foreground audio. For background audio, the service indicates whether the background audio is mixable. For foreground audio, the service indicates an interrupt behavior. When the local device is playing background audio and receives foreground audio, the background audio is paused, attenuated, or not changed based on the indicated interrupt behavior of the foreground audio and whether the background audio has been designated as being mixable.

Abstract: Features are disclosed for generating markers for elements or other portions of an audio presentation so that a speech processing system may determine which portion of the audio presentation a user utterance refers to. For example, an utterance may include a pronoun with no explicit antecedent. The marker may be used to associate the utterance with the corresponding content portion for processing. The markers can be provided to a client device with a text-to-speech (“TTS”) presentation. The markers may then be provided to a speech processing system along with a user utterance captured by the client device. The speech processing system, which may include automatic speech recognition (“ASR”) modules and/or natural language understanding (“NLU”) modules, can generate hints based on the marker. The hints can be provided to the ASR and/or NLU modules in order to aid in processing the meaning or intent of a user utterance.

Abstract: Network-based services may be provided to a user through the user of a speech-based user device located within a user environment. The speech-based user device may accept speech commands from a user and may also interact with the user by means of generated speech. Operating state of the speech-based user device may be provided to the network-based service and stored by the service. Applications that provide services through the speech-based interface may request and obtain the stored state information.