Abstract: A method for predicting parametric vocoder parameter includes receiving a text utterance having one or more words, each word having one or more syllables, and each syllable having one or more phonemes. The method also includes receiving, as input to a vocoder model, prosodic features that represent an intended prosody for the text utterance and a linguistic specification. The prosodic features include a duration, pitch contour, and energy contour for the text utterance, while the linguistic specification includes sentence-level linguistic features, word-level linguistic features for each word, syllable-level linguistic features for each syllable, and phoneme-level linguistic features for each phoneme. The method also includes predicting vocoder parameters based on the prosodic features and the linguistic specification.

Abstract: A method for predicting parametric vocoder parameter includes receiving a text utterance having one or more words, each word having one or more syllables, and each syllable having one or more phonemes. The method also includes receiving, as input to a vocoder model, prosodic features that represent an intended prosody for the text utterance and a linguistic specification. The prosodic features include a duration, pitch contour, and energy contour for the text utterance, while the linguistic specification includes sentence-level linguistic features, word-level linguistic features for each word, syllable-level linguistic features for each syllable, and phoneme-level linguistic features for each phoneme. The method also includes predicting vocoder parameters based on the prosodic features and the linguistic specification.

Abstract: Systems and methods for synthesizing speech based on received text and one or more emulated speech parameters. Text is received with one or more emulated speech parameters that indicate one or more features for the synthesized speech. Synthesized speech audio is generated based on the received parameters. The synthesized speech audio data is provided to an emulated microphone component that provides the synthesized audio to an automatic speech recognizer. The automatic speech recognizer utilizes one or more speech recognition models to generate converted text based on the synthesized speech audio data.

Abstract: According to an aspect, a method includes storing messages exchanged on a messaging platform in a non-relational database, obtaining a database snapshot of the non-relational database, executing a database task on the database snapshot, and generating, in response to the database task, an update log, where the update log identifies a first record to be changed or deleted in the non-relational database. The method includes determining whether or not the first record identified in the update log has been updated in the non-relational database after a time instance associated with the database task and applying the change or deletion of the first record in the non-relational database in response to the first record being determined as not updated after the time instance associated with the database task.

Abstract: A method for predicting parametric vocoder parameter includes receiving a text utterance having one or more words, each word having one or more syllables, and each syllable having one or more phonemes. The method also includes receiving, as input to a vocoder model, prosodic features that represent an intended prosody for the text utterance and a linguistic specification. The prosodic features include a duration, pitch contour, and energy contour for the text utterance, while the linguistic specification includes sentence-level linguistic features, word-level linguistic features for each word, syllable-level linguistic features for each syllable, and phoneme-level linguistic features for each phoneme. The method also includes predicting vocoder parameters based on the prosodic features and the linguistic specification.

Abstract: A method for predicting parametric vocoder parameter includes receiving a text utterance having one or more words, each word having one or more syllables, and each syllable having one or more phonemes. The method also includes receiving, as input to a vocoder model, prosodic features that represent an intended prosody for the text utterance and a linguistic specification. The prosodic features include a duration, pitch contour, and energy contour for the text utterance, while the linguistic specification includes sentence-level linguistic features, word-level linguistic features for each word, syllable-level linguistic features for each syllable, and phoneme-level linguistic features for each phoneme. The method also includes predicting vocoder parameters based on the prosodic features and the linguistic specification.

Abstract: Systems and methods for extracting information from documents are provided. In one example embodiment, a computer-implemented method includes obtaining one or more units of text from an image of a document. The method includes determining one or more annotated values from the one or more units of text and determining a set of candidate labels for each annotated value. The method determines each set of candidate labels by performing a search for the candidate labels based at least in part on a language associated with the document and a location of each annotated value. The method includes determining a canonical label for each annotated value based at least in part on the associated candidate labels, and mapping at least one annotated value to an action that is presented to a user based at least in part on the canonical label associated with the annotated value.