Google Inc.

Thomas Edward Bagby

Russell John Wyatt Skerry-Ryan

Sean Matthew Shannon

Daisy Stanton

Soroosh Mariooryad

Eric Dean Battenberg

David Teh-hwa Kao

Hyung-Jin Kim

Izhak Shafran

Moustafa A Hammad

Rajan Patel

Russell John-Wyatt Skerry-Ryan

David Teh-Hwa Kao

Systems and methods for text-to-speech with novel speakers can obtain text data and output audio data. The input text data may be input along with one or more speaker preferences. The speaker preferences can include speaker characteristics. The speaker preferences can be processed by a machine-learned model conditioned on a learned prior distribution to determine a speaker embedding. The speaker embedding can then be processed with the text data to generate an output that includes audio data descriptive of the text data spoken by a novel speaker.

Neural-network-based text-to-speech model for novel speaker generation

A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.

Variational embedding capacity in expressive end-to-end speech synthesis

A system for generating an output audio signal includes a context encoder, a text-prediction network, and a text-to-speech (TTS) model. The context encoder is configured to receive one or more context features associated with current input text and process the one or more context features to generate a context embedding associated with the current input text. The text-prediction network is configured to process the current input text and the context embedding to predict, as output, a style embedding for the current input text. The style embedding specifies a specific prosody and/or style for synthesizing the current input text into expressive speech. The TTS model is configured to process the current input text and the style embedding to generate an output audio signal of expressive speech of the current input text. The output audio signal has the specific prosody and/or style specified by the style embedding.

Controlling expressivity in end-to-end speech synthesis systems

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex evolution recurrent neural networks. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A first vector sequence comprising audio features determined from the audio data is generated. A second vector sequence is generated, as output of a first recurrent neural network in response to receiving the first vector sequence as input, where the first recurrent neural network has a transition matrix that implements a cascade of linear operators comprising (i) first linear operators that are complex-valued and unitary, and (ii) one or more second linear operators that are non-unitary. An output vector sequence of a second recurrent neural network is generated. A transcription for the utterance is generated based on the output vector sequence generated by the second recurrent neural network. The transcription for the utterance is provided.

Complex evolution recurrent neural networks

Methods, systems, and apparatus for determining resource quality based on resource competition. In an aspect, a method comprises: for each of a plurality of resource locators: generating first value for the resource locator that indicates, for a plurality of first sets of search results that each include the resource locator, a number of occurrences of other resource locators that were impressed and not selected when the resource locator was selected; generating a second value for the resource locator that indicates, for a plurality of second sets of search results that each include the resource locator, a number of occurrences of other resource locators that were selected when the resource locator was impressed and not selected; and generating, based on a difference between the first value and the second value, an adjustment factor for the resource locator for adjusting a score associated with the resource locator during a search operation.

Growing community of inventors

San Francisco, CA, United States of America

Thomas Edward Bagby