Amazon Technologies, Inc.

Jaime Lorenzo Trueba

Thomas Renaud Drugman

Andrew Paul Breen

Thomas Edward Merritt

Viacheslav Klimkov

Roberto Barra-Chicote

Srikanth Ronanki

Sri Vishnu Kumar Karlapati

Abdigani Mohamed Diriye

Alejandro Ricardo Mottini d'Oliveira

Patryk Golebiowski

Piotr Jozwiak

Panagiota Karanasou

Arnaud Vincent Pierre Yves Joly

Syed Ammar Abbas

Alexis Pierre Moinet

A speech-processing system receives first audio data correspond to a first voice and second audio data corresponding to a second voice. The speech-processing system determines vocal characteristics of the second voice and determines output corresponding to the first audio data and the vocal characteristics.

Synthetic speech processing

During text-to-speech processing, a speech model creates output audio data, including speech, that corresponds to input text data that includes a representation of the speech. A spectrogram estimator estimates a frequency spectrogram of the speech; the corresponding frequency-spectrogram data is used to condition the speech model. A plurality of acoustic features corresponding to different segments of the input text data, such as phonemes, syllable-level features, and/or word-level features, may be separately encoded into context vectors; the spectrogram estimator uses these separate context vectors to create the frequency spectrogram.

Text-to-speech (TTS) processing

A speech-processing system receives input data corresponding to one or more characteristics of speech. The system determines parameters representing the characteristics and, using the parameters, encoded values corresponding to the characteristics. A speech synthesis component of the speech-processing processes the encoded values to determine audio data including a representation of the speech and corresponding to the characteristics.

Devices and techniques are generally described for learned condition text-to-speech synthesis. In some examples, first data representing a selection of a type of prosodic expressivity may be received. In some further examples, a selection of content comprising text data may be received. First audio data may be determined that includes an audio representation of the text data. The first audio data may be generated based at least in part on sampling from a first latent distribution generated using a conditional primary variational autoencoder (VAE). The sampling from the first latent distribution may be conditioned on a first learned distribution associated with the type of prosodic expressivity. In various examples, the first audio data may be sent to a first computing device.

Learned condition text-to-speech synthesis

Growing community of inventors

Cambridge, United Kingdom

Jaime Lorenzo Trueba