ASR2K: Speech recognition for around 2000 languages without audio

X Li, F Metze, DR Mortensen, AW Black… - ar**, features input, and source language selection
P Do, M Coler, J Dijkstra, E Klabbers - ar** method and using phonological
features input in transfer learning for TTS in low-resource languages. We use diverse source …

GE2PE: Persian End-to-End Grapheme-to-Phoneme Conversion

E Rahmati, H Sameti - Findings of the Association for …, 2024 - aclanthology.org
Abstract Text-to-Speech (TTS) systems have made significant strides, enabling the
generation of speech from grapheme sequences. However, for low-resource languages …

The SIGMORPHON 2022 Shared Task on Cross-lingual and Low-Resource Grapheme-to-Phoneme Conversion

AD McCarthy, JL Lee, A DeLucia… - Proceedings of the …, 2023 - aclanthology.org
Grapheme-to-phoneme conversion is an important component in many speech
technologies, but until recently there were no multilingual benchmarks for this task. The third …

Text-Inductive Graphone-Based Language Adaptation for Low-Resource Speech Synthesis

T Saeki, S Maiti, X Li, S Watanabe… - … on Audio, Speech …, 2024 - ieeexplore.ieee.org
Neural text-to-speech (TTS) systems have made significant progress in generating natural
synthetic speech. However, neural TTS requires large amounts of paired training data …

Meta Learning Text-to-Speech Synthesis in over 7000 Languages

F Lux, S Meyer, L Behringer, F Zalkow, P Do… - arxiv preprint arxiv …, 2024 - arxiv.org
In this work, we take on the challenging task of building a single text-to-speech synthesis
system that is capable of generating speech in over 7000 languages, many of which lack …