This embedding captures characteristics of the audio that are independent of phonetic information and idiosyncratic speaker traits - these are attributes like stress, intonation, and timing. For technical details, please refer to the paper. The lower half of the image is the original Tacotron sequence-to-sequence model. We augment Tacotron with a prosody encoder. We augment the Tacotron architecture with an additional prosody encoder that computes a low-dimensional embedding from a clip of human speech (the reference audio).

Our first paper, “ Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron”, introduces the concept of a prosody embedding. Today, we are excited to share two new papers that address these problems. This may lead to monotonous-sounding speech, even when models are trained on very expressive datasets like audiobooks, which often contain character voices with significant variation. Most current end-to-end systems, including Tacotron, don't explicitly model prosody, meaning they can't control exactly how the generated speech should sound.

To deliver a truly human-like voice, however, a TTS system must learn to model prosody, the collection of expressive factors of speech, such as intonation, stress, and rhythm. This will help us build better human-computer interfaces, like conversational assistants, audiobook narration, news readers, or voice design software.

In particular, end-to-end architectures, such as the Tacotron systems we announced last year, can both simplify voice building pipelines and produce natural-sounding speech. Posted by Yuxuan Wang, Research Scientist and RJ Skerry-Ryan, Software Engineer, on behalf of the Machine Perception, Google Brain and TTS Research teamsĪt Google, we're excited about the recent rapid progress of neural network-based text-to-speech (TTS) research.

Half life text to speech