Bonan Zheng

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… Show more

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. Show less

Methods and systems for managing application performance in a distributed computing environment. Embodiments commence when an application seeks to perform a function over a content object. The application submits a request to perform the function on the content object, and the request is received by an application programming interface processor. The application programming interface processor accesses a data structure comprising entries that relate the requested function to one or more code… Show more

Methods and systems for managing application performance in a distributed computing environment. Embodiments commence when an application seeks to perform a function over a content object. The application submits a request to perform the function on the content object, and the request is received by an application programming interface processor. The application programming interface processor accesses a data structure comprising entries that relate the requested function to one or more code instances that are accessible at one or more code locations. An evaluator predicts performance of the function using a first location of a first code instance and compares that predicted performance to a predicted or measured performance of the same function using a second location of a second code instance that implements the same function. The better performing code instance at the determined code location is invoked. Results are collated, formatted, and returned to the calling application. Show less

Techniques for determining when speech is directed at another individual of a dialog, and storing a representation of such user-directed speech for use as context when processing subsequently-received system-directed speech are described. A system receives audio data and/or video data and determines therefrom that speech in the audio data is user-directed. Based on this, the system determine whether the speech is able to be used to perform an action by the system. If the speech is able to be… Show more

Techniques for determining when speech is directed at another individual of a dialog, and storing a representation of such user-directed speech for use as context when processing subsequently-received system-directed speech are described. A system receives audio data and/or video data and determines therefrom that speech in the audio data is user-directed. Based on this, the system determine whether the speech is able to be used to perform an action by the system. If the speech is able to be used to perform an action, the system stores a natural language representation of the speech. Thereafter, when the system receives system-directed speech, the system generates a rewrite of a natural language representation of the system-directed speech based on the previously-received user-directed speech. The system then determines output data responsive to the system-directed speech using the rewritten natural language representation. Show less