TUNDRA: a multilingual corpus of found data for TTS research created with light supervision
Abstract Simple4All Tundra (version 1.0) is the first release of a standardised multilingual
corpus designed for text-to-speech research with imperfect or found data. The corpus …
corpus designed for text-to-speech research with imperfect or found data. The corpus …
ALISA: An automatic lightly supervised speech segmentation and alignment tool
This paper describes the ALISA tool, which implements a lightly supervised method for
sentence-level alignment of speech with imperfect transcripts. Its intended use is to enable …
sentence-level alignment of speech with imperfect transcripts. Its intended use is to enable …
Unsupervised and lightly-supervised learning for rapid construction of TTS systems in multiple languages fromfound'data: evaluation and analysis
This paper presents techniques for building text-to-speech frontends in a way that avoids the
need for language-specific expert knowledge, but instead relies on universal resources …
need for language-specific expert knowledge, but instead relies on universal resources …
A preliminary Plains Cree speech synthesizer
A Harrigan, T Mills, A Arppe - Proceedings of the Workshop …, 2019 - journals.colorado.edu
This paper discusses the development and evaluation of a Speech Synthesizer for Plains
Cree, an Algonquian language of North America. Synthesis is achieved using Simple4All …
Cree, an Algonquian language of North America. Synthesis is achieved using Simple4All …
[PDF][PDF] Investigating the Robustness of Sequence-to-Sequence Text-to-Speech Models to Imperfectly-Transcribed Training Data.
Abstract Sequence-to-sequence (S2S) text-to-speech (TTS) models can synthesise high
quality speech when large amounts of annotated training data are available. Transcription …
quality speech when large amounts of annotated training data are available. Transcription …
Controlling text-to-speech pronunciation using limited linguistic resources
J Fong - 2024 - era.ed.ac.uk
Correct pronunciation is essential for high-quality text-to-speech (TTS) systems. To achieve
this, the majority of TTS systems rely on phonemes as an intermediate representation …
this, the majority of TTS systems rely on phonemes as an intermediate representation …
The Simple4All entry to the blizzard challenge 2013
O Watts, A Stan, Y Mamiya, A Suni… - Proc. Blizzard …, 2013 - research.ed.ac.uk
We describe the synthetic voices entered into the 2013 Blizzard Challenge by the
SIMPLE4ALL consortium. The 2013 Blizzard Challenge presents an opportunity to test and …
SIMPLE4ALL consortium. The 2013 Blizzard Challenge presents an opportunity to test and …
Building synthetic voices for under-resourced languages: The feasibility of using audiobook data
F de Wet, W Van der Walt, N Dlamini… - … Association of South …, 2017 - ieeexplore.ieee.org
Creating synthetic voices that are natural and intelligible is a daunting challenge for well-
resourced languages. The challenge is much bigger for languages in which the speech and …
resourced languages. The challenge is much bigger for languages in which the speech and …
Combining lightly-supervised learning and user feedback to construct andimprove a statistical parametric speech synthesizer for malay
In this study, we aim to reduce the human effort in preparing training data for synthesizing
human speech and improve the quality of synthetic speech. In spite of the learning-from-data …
human speech and improve the quality of synthetic speech. In spite of the learning-from-data …
[图书][B] Query-by-Example Spoken Term Detection for Low-resource Languages
H Wang - 2014 - search.proquest.com
In this thesis, we consider the problem of query-by-example (QbyE) spoken term detection
(STD) for low-resource languages. The problem is to automatically detect and locate the …
(STD) for low-resource languages. The problem is to automatically detect and locate the …