Saved in:
Bibliographic Details
Main Authors: Łajszczak, Mateusz, Cámbara, Guillermo, Li, Yang, Beyhan, Fatih, van Korlaar, Arent, Yang, Fan, Joly, Arnaud, Martín-Cortinas, Álvaro, Abbas, Ammar, Michalski, Adam, Moinet, Alexis, Karlapati, Sri, Muszyńska, Ewa, Guo, Haohan, Putrycz, Bartosz, Gambino, Soledad López, Yoo, Kayeon, Sokolova, Elena, Drugman, Thomas
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.08093
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916126823284736
author Łajszczak, Mateusz
Cámbara, Guillermo
Li, Yang
Beyhan, Fatih
van Korlaar, Arent
Yang, Fan
Joly, Arnaud
Martín-Cortinas, Álvaro
Abbas, Ammar
Michalski, Adam
Moinet, Alexis
Karlapati, Sri
Muszyńska, Ewa
Guo, Haohan
Putrycz, Bartosz
Gambino, Soledad López
Yoo, Kayeon
Sokolova, Elena
Drugman, Thomas
author_facet Łajszczak, Mateusz
Cámbara, Guillermo
Li, Yang
Beyhan, Fatih
van Korlaar, Arent
Yang, Fan
Joly, Arnaud
Martín-Cortinas, Álvaro
Abbas, Ammar
Michalski, Adam
Moinet, Alexis
Karlapati, Sri
Muszyńska, Ewa
Guo, Haohan
Putrycz, Bartosz
Gambino, Soledad López
Yoo, Kayeon
Sokolova, Elena
Drugman, Thomas
contents We introduce a text-to-speech (TTS) model called BASE TTS, which stands for $\textbf{B}$ig $\textbf{A}$daptive $\textbf{S}$treamable TTS with $\textbf{E}$mergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain speech data, achieving a new state-of-the-art in speech naturalness. It deploys a 1-billion-parameter autoregressive Transformer that converts raw texts into discrete codes ("speechcodes") followed by a convolution-based decoder which converts these speechcodes into waveforms in an incremental, streamable manner. Further, our speechcodes are built using a novel speech tokenization technique that features speaker ID disentanglement and compression with byte-pair encoding. Echoing the widely-reported "emergent abilities" of large language models when trained on increasing volume of data, we show that BASE TTS variants built with 10K+ hours and 500M+ parameters begin to demonstrate natural prosody on textually complex sentences. We design and share a specialized dataset to measure these emergent abilities for text-to-speech. We showcase state-of-the-art naturalness of BASE TTS by evaluating against baselines that include publicly available large-scale text-to-speech systems: YourTTS, Bark and TortoiseTTS. Audio samples generated by the model can be heard at https://amazon-ltts-paper.com/.
format Preprint
id arxiv_https___arxiv_org_abs_2402_08093
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
Łajszczak, Mateusz
Cámbara, Guillermo
Li, Yang
Beyhan, Fatih
van Korlaar, Arent
Yang, Fan
Joly, Arnaud
Martín-Cortinas, Álvaro
Abbas, Ammar
Michalski, Adam
Moinet, Alexis
Karlapati, Sri
Muszyńska, Ewa
Guo, Haohan
Putrycz, Bartosz
Gambino, Soledad López
Yoo, Kayeon
Sokolova, Elena
Drugman, Thomas
Machine Learning
Computation and Language
Audio and Speech Processing
We introduce a text-to-speech (TTS) model called BASE TTS, which stands for $\textbf{B}$ig $\textbf{A}$daptive $\textbf{S}$treamable TTS with $\textbf{E}$mergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain speech data, achieving a new state-of-the-art in speech naturalness. It deploys a 1-billion-parameter autoregressive Transformer that converts raw texts into discrete codes ("speechcodes") followed by a convolution-based decoder which converts these speechcodes into waveforms in an incremental, streamable manner. Further, our speechcodes are built using a novel speech tokenization technique that features speaker ID disentanglement and compression with byte-pair encoding. Echoing the widely-reported "emergent abilities" of large language models when trained on increasing volume of data, we show that BASE TTS variants built with 10K+ hours and 500M+ parameters begin to demonstrate natural prosody on textually complex sentences. We design and share a specialized dataset to measure these emergent abilities for text-to-speech. We showcase state-of-the-art naturalness of BASE TTS by evaluating against baselines that include publicly available large-scale text-to-speech systems: YourTTS, Bark and TortoiseTTS. Audio samples generated by the model can be heard at https://amazon-ltts-paper.com/.
title BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
topic Machine Learning
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2402.08093