An example method includes receiving, by a computational assistant executing at one or more processors of a mobile computing device and via a wireless link between the mobile computing device and an external device, a representation of audio data generated by a microphone of the external device, the audio data representing a spoken utterance detected by the external device; determining, by the computational assistant and based on the audio data, a response to the spoken utterance; and sending, by the mobile computing device, to the external device, and via the wireless link between the mobile computing device and the external device, a command to output, for playback by one or more speakers connected to the external device via a hardwired analog removable connector of the external device or a wireless link between the external device and the one or more speakers, audio data representing the response to the spoken utterance.

An example method includes receiving, by a computational assistant executing at one or more processors of a mobile computing device and via a wireless link between the mobile computing device and an external device, a representation of audio data generated by a microphone of the external device, the audio data representing a spoken utterance detected by the external device; determining, by the computational assistant and based on the audio data, a response to the spoken utterance; and sending, by the mobile computing device, to the external device, and via the wireless link between the mobile computing device and the external device, a command to output, for playback by one or more speakers connected to the external device via a hardwired analog removable connector of the external device or a wireless link between the external device and the one or more speakers, audio data representing the response to the spoken utterance.

Systems and methods are described for recommending a content item. A search query for a content item is received. The availability of the content item from more than one source is determined. In response to determining that the content item is available from more than one source, the quality of each of the available content items from respective sources is determined. A recommendation factor is determined. The recommendation factor is based on at least one of the bandwidth available to a user device, the resolution capability of the user device, and the quality of experience of each of the sources from which the content item is available. A list of search results for the available content items is generated. The list is ordered based on the quality of each of the available content items from respective sources and the recommendation factor.

A media content item recommendation system recommends media content items based on one or more attributes of a seed playlist. The recommended media content items can be determined from a plurality of existing playlists that have been created over a period of time. Such existing playlists can be selected based on similarity to the seed playlist.

A media content item recommendation system recommends media content items based on one or more attributes of a seed playlist. The recommended media content items can be determined from a plurality of existing playlists that have been created over a period of time. Such existing playlists can be selected based on similarity to the seed playlist.

A method of displaying media content on a display screen of a communication device. The method includes receiving an indication of a state transition of a first Activity of an application program being executed on a processor of the communication device. The processor, in response to the indication, executes program code in order to monitor a memory state of the operating system so as to determine a user interface state associated with the first Activity. The processor further determines whether the first Activity is finishing based at least in part on the user interface state. Upon determining the first Activity is finishing, the processor causes the media content to be displayed upon further determining that a predetermined condition associated with the communication device exists.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining breakpoints in a media item. Methods can include determining a candidate set of breakpoints within a media item. A machine learning model is used to generate a score for each particular candidate breakpoint in the set of candidate breakpoints based on presentation features of the media item. A subset of candidate breakpoints is selected from the set of candidate breakpoints based on the score. A final set of breakpoints is selected from the subset of candidate breakpoints based on a combination of the score for each particular candidate breakpoint and a location of the particular candidate breakpoint relative to a different candidate breakpoint. The final set of breakpoints is stored in a database and during playback of the media item, a digital component is presented when the media item reaches a stored breakpoint.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining breakpoints in a media item. Methods can include determining a candidate set of breakpoints within a media item. A machine learning model is used to generate a score for each particular candidate breakpoint in the set of candidate breakpoints based on presentation features of the media item. A subset of candidate breakpoints is selected from the set of candidate breakpoints based on the score. A final set of breakpoints is selected from the subset of candidate breakpoints based on a combination of the score for each particular candidate breakpoint and a location of the particular candidate breakpoint relative to a different candidate breakpoint. The final set of breakpoints is stored in a database and during playback of the media item, a digital component is presented when the media item reaches a stored breakpoint.

An electronic device generates a score for each objective in a hierarchy of objectives. Generating the score comprises using a representation of the media content item and a user as inputs to a first machine learning algorithm, to generate a score for a first objective corresponding to a first level in the hierarchy of the objectives and using an output of the first machine learning algorithm, distinct from the score for the first objective, as an input to a second machine learning algorithm to generate a score for a second objective corresponding to a second level in the hierarchy of objectives. The electronic device generates a respective score between the user and the media content item using the score for the first objective and the score for the second objective and provides media content to the user based on the respective scores.

An electronic device generates a score for each objective in a hierarchy of objectives. Generating the score comprises using a representation of the media content item and a user as inputs to a first machine learning algorithm, to generate a score for a first objective corresponding to a first level in the hierarchy of the objectives and using an output of the first machine learning algorithm, distinct from the score for the first objective, as an input to a second machine learning algorithm to generate a score for a second objective corresponding to a second level in the hierarchy of objectives. The electronic device generates a respective score between the user and the media content item using the score for the first objective and the score for the second objective and provides media content to the user based on the respective scores.