Google Inc.

Matthias Quasthoff

Simon Tokumine

Benedict Davies

Jack Whyte

Alessio Macri

Jakub Adamek

Guillaume Boniface

Simon Tickner

Jakob Nicolaus Foerster

A computing system and related techniques for selecting content to be automatically converted to speech and provided as an audio signal are provided. A text-to-speech request associated with a first document can be received that includes data associated with a playback position of a selector associated with a text-to-speech interface overlaid on the first document. First content associated with the first document can be determined based at least in part on the playback position, the first content including content that is displayed in the user interface at the playback position. The first document can be analyzed to identify one or more structural features associated with the first content. Speech data can be generated based on the first content and the one or more structural features.

Systems and methods for a text-to-speech interface

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating direct speech messages based on voice commands that include indirect speech messages. In one aspect, a method includes receiving a voice input corresponding to an utterance. A determination is made whether a transcription of the utterance includes a command to initiate a communication to a user and a segment that is classified as indirect speech. In response to determining that the transcription of the utterance includes the command and the segment that is classified as indirect speech, the segment that is classified as indirect speech is provided as input to a machine translator. In response to providing the segment that is classified as indirect speech to the machine translator, a direct speech segment is received from the machine translator. A communication is initiated that includes the direct speech segment.

Machine translation of indirect speech

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for suggesting a phrase for performing a voice action. The methods, systems, and apparatus include actions of classifying a received phrase as an incomplete phrase for performing a voice action based at least on determining that (i) the voice action requires a parameter, and (ii) that no term of the phrase corresponds to the parameter. Additional actions include, in response to classifying the phrase as an incomplete phrase, generating a prompt for entry of the parameter, and in response to the prompt, receiving data indicating an entered parameter. Further actions include providing, for output, a suggested complete phrase for performing the voice action using the entered parameter.

Suggested query constructor for voice actions

Growing community of inventors

London, United Kingdom

Matthias Quasthoff