Augmented datasheets for speech datasets and ethical decision-making
Speech datasets are crucial for training Speech Language Technologies (SLT); however,
the lack of diversity of the underlying training data can lead to serious limitations in building …
the lack of diversity of the underlying training data can lead to serious limitations in building …
[PDF][PDF] Siri on-device deep learning-guided unit selection text-to-speech system.
T Capes, P Coles, A Conkie, L Golipour… - Interspeech, 2017 - academia.edu
This paper describes Apple's hybrid unit selection speech synthesis system, which provides
the voices for Siri with the requirement of naturalness, personality and expressivity. It has …
the voices for Siri with the requirement of naturalness, personality and expressivity. It has …
[PDF][PDF] The reference corpus of the contemporary Romanian language (CoRoLa)
We present here the largest publicly available corpus of Romanian. Its written component
contains 1,257,752,812 tokens, distributed, in an unbalanced way, in several language …
contains 1,257,752,812 tokens, distributed, in an unbalanced way, in several language …
RSC: A Romanian read speech corpus for automatic speech recognition
Although many efforts have been made in the last decade to enhance the speech and
language resources for Romanian, this language is still considered under-resourced. While …
language resources for Romanian, this language is still considered under-resourced. While …
A processing platform relating data and tools for Romanian language
This paper presents RELATE (http://relate. racai. ro), a high-performance natural language
platform designed for Romanian language. It is meant both for demonstration of available …
platform designed for Romanian language. It is meant both for demonstration of available …
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 …
Unsupervised learning for text-to-speech synthesis
OS Watts - 2013 - era.ed.ac.uk
This thesis introduces a general method for incorporating the distributional analysis of
textual and linguistic objects into text-to-speech (TTS) conversion systems. Conventional …
textual and linguistic objects into text-to-speech (TTS) conversion systems. Conventional …
[PDF][PDF] Towards a romanian end-to-end automatic speech recognition based on deepspeech2
This paper presents an implementation of an ASR system for the Romanian language that
uses a multi-layer neural network architecture to transcribe the input speech, augmented …
uses a multi-layer neural network architecture to transcribe the input speech, augmented …
The SWARA speech corpus: A large parallel Romanian read speech dataset
This paper introduces one of the largest Romanian speech datasets freely available for both
academic and commercial use. The dataset comprises speech data recorded over the last …
academic and commercial use. The dataset comprises speech data recorded over the last …
[HTML][HTML] Improving post-filtering of artificial speech using pre-trained LSTM neural networks
M Coto-Jiménez - Biomimetics, 2019 - mdpi.com
Several researchers have contemplated deep learning-based post-filters to increase the
quality of statistical parametric speech synthesis, which perform a mapping of the synthetic …
quality of statistical parametric speech synthesis, which perform a mapping of the synthetic …