ResearchSpace
→
Browsing by Author

Browsing by Author "Louw, Johannes A"

Now showing items 1-11 of 11

Automatic stylization, coding and modelling of intonation in text-to-speech for under-resourced languages

Author: Louw, Johannes A ; Moodley, Avashlin Date: Dec 2017 In this paper an automatic method to implicitly model intonation for statistical parametric speech synthesis (SPSS) is presented. The approach is ideally suited to single speaker speech databases as used in text-to-speech (TTS), due to the ... Read more
AwezaMed: A multilingual, multimodal speech-to-speech translation application for maternal health care

Author: Marais, Laurette ; Louw, Johannes A ; Badenhorst, Jacob AC ; Calteaux, Karen V ; Wilken, Ilana ; Van Niekerk, Nina ; Stein, Glenn Date: Jul 2020 The language contexts of multilingual developing countries such as South Africa are often characterised by communication challenges resulting from language differences. AwezaMed is a multilingual, multimodal speech-to-speech translation ... Read more
Cross-lingual transfer using phonological features for resource-scarce text-to-speech

Author: Louw, Johannes A Date: Aug 2023 In this work, we explore the use of phonological features incross-lingual transfer within resource-scarce settings. We modify the architecture of VITS to accept a phonological feature vector as input, instead of phonemes or characters. ... Read more
Halfphones: a backoff mechanism for Diphone Unit Selection Synthesis

Author: Louw, Johannes A ; Davel, M Date: Nov 2006 Diphone-based speech synthesis has been researched for many years, and some of the most successful concatenative synthesis systems employ diphones. Such systems can produce very intelligible synthetic speech, but tend not to sound completely ... Read more
Neural speech synthesis for resource-scarce languages

Author: Louw, Johannes A Date: Dec 2019 Recent work in sequence-to-sequence neural networks with attention mechanisms, such as the Tacotron 2 and DCTTS architectures, have brought on substantial naturalness improvements in synthesised speech. These architectures require at least ... Read more
Rhonda: The architecture of a multilingual speech-to-speech translation pipeline

Author: Louw, Johannes A ; Moodley, Avashlin Date: Dec 2018 Speech-to-speech translation can be described as converting a speech signal from a source language into a speech signal of the same meaning or intent into a target language. This process is achieved by the coordinated cooperation of individual ... Read more
Speaker specific phrase break modeling with conditional random fields for text-to-speech

Author: Louw, Johannes A ; Moodley, Avashlin Date: Dec 2016 In this paper we present a new cascading conditional random field based phrase break model for text-to-speech systems, trained on the speaker specific acoustic data that the text-to-speech voices are trained on. The training phase does not ... Read more
The Speect text-to-speech entry for the Blizzard Challenge 2016

Author: Louw, Johannes A ; Moodley, Avashlin ; Govender, Avashna Date: Sep 2016 This paper describes the Speect text-to-speech system entry submitted to the Blizzard Challenge 2016. The focus of this entry was to build a data driven text-to-speech system that generates an expressive voice suitable for children’s audio ... Read more
The Speect text-to-speech system entry for the Blizzard Challenge 2013

Author: Louw, Johannes A ; Schlunz, Georg I ; Van der Walt, W ; De Wet, Febe ; Pretorius, L Date: Sep 2013 This paper describes the speect text-to-speech system entry for the Blizzard Challenge 2013. The techniques applied for the tasks of the challenge are described as well as the implementation details for the alignment of the audio books and ... Read more
Speect: a multilingual text-to-speech system

Author: Louw, Johannes A Date: Nov 2008 This paper introduces a new multilingual text-to-speech system, which we call Speect (Speech synthesis with extensible architecture), aiming to address the shortcomings of using Festival as a research sytem and Flite as a deployment system ... Read more
Text-to-speech duration models for resource-scarce languages in neural architectures

Author: Louw, Johannes A Date: Dec 2020 Sequence-to-sequence end-to-end models for text-to-speech have shown significant gains in naturalness of the produced synthetic speech. These models have an encoder-decoder architecture, without an explicit duration model, but rather a learned ... Read more

Now showing items 1-11 of 11

Browse

All of ResearchSpace

Quick Links

Legislation and compliance

General Enquiries

Tel: + 27 12 841 2911
Email: callcentre@csir.co.za

Physical Address
Meiring Naudé Road
Brummeria
Pretoria
South Africa

Postal Address
PO Box 395
Pretoria 0001
South Africa

Social Connect

Resources on this site are free to download and reuse according to associated licensing provision. Please read the terms and conditions of usage of each resource.

Browsing by Author "Louw, Johannes A"

Browsing by Author "Louw, Johannes A"

Browse

All of ResearchSpace

Quick Links

Legislation and compliance

General Enquiries

Social Connect