no code implementations • 17 Aug 2021 • Javier Latorre, Charlotte Bailleul, Tuuli Morrill, Alistair Conkie, Yannis Stylianou
In this work, we explore multiple architectures and training procedures for developing a multi-speaker and multi-lingual neural TTS system with the goals of a) improving the quality when the available data in the target language is limited and b) enabling cross-lingual synthesis.
no code implementations • 10 Apr 2020 • Alistair Conkie, Andrew Finch
We take a Machine Translation (MT) inspired approach to constructing the frontend, and model both text normalization and pronunciation on a sentence level by building and using sequence-to-sequence (S2S) models.
no code implementations • 10 Apr 2020 • Soumi Maiti, Erik Marchi, Alistair Conkie
We demonstrate that a bilingual speaker embedding space contains a separate distribution for each language and that a simple transform in speaker space generated by the speaker embedding can be used to control the degree of accent of a synthetic voice in a language.
no code implementations • LREC 2012 • Alistair Conkie, Thomas Okken, Yeon-Jun Kim, Giuseppe Di Fabbrizio
The AT{\&}T VoiceBuilder provides a new tool to researchers and practitioners who want to have their voices synthesized by a high-quality commercial-grade text-to-speech system without the need to install, configure, or manage speech processing software and equipment. It is implemented as a web service on the AT{\&}T Speech Mashup Portal. The system records and validates users' utterances, processes them to build a synthetic voice and provides a web service API to make the voice available to real-time applications through a scalable cloud-based processing platform.