Amazon Technologies, Inc.

Bajibabu Bollepalli

Thomas Renaud Drugman

Panagiota Karanasou

Sri Vishnu Kumar Karlapati

Arnaud Vincent Pierre Yves Joly

Syed Ammar Abbas

Simon Slangen

Alexis Pierre Moinet

Petr Makarov

Techniques for performing text-to-speech are described. An exemplary method includes receiving a request to generate audio from input text; generating audio from the input text by: generating a first number of vectors from phoneme embeddings representing the input text, predicting one or more spectrograms having the first number of frames using multiple scales wherein a coarser scale influences a finer scale, concatenating the first number of vectors and the predicted one or more spectrograms, generating at least one mel spectrogram from the concatenated vectors and the predicted one or more spectrograms, and converting, with a vocoder, the at least one mel spectrogram frames to audio; and outputting the generated audio according to the request.

Multi-scale spectrogram text-to-speech

Growing community of inventors

Cambridge, United Kingdom

Bajibabu Bollepalli