S
Stephen Renals
Researcher at University of Edinburgh
Publications - 6
Citations - 329
Stephen Renals is an academic researcher from University of Edinburgh. The author has contributed to research in topics: Speech synthesis & Hidden Markov model. The author has an hindex of 4, co-authored 6 publications receiving 298 citations.
Papers
More filters
Proceedings ArticleDOI
A study of speaker adaptation for DNN-based speech synthesis
TL;DR: An experimental analysis of speaker adaptation for DNN-based speech synthesis at different levels and systematically analyse the performance of each individual adaptation technique and that of their combinations.
Proceedings ArticleDOI
A Study of the Recurrent Neural Network Encoder-Decoder for Large Vocabulary Speech Recognition
TL;DR: This paper studies the RNN encoder-decoder approach for large vocabulary end-to-end speech recognition, whereby an encoder transforms a sequence of acoustic vectors into a sequences of feature representations, from which a decoder recovers asequence of words.
Journal ArticleDOI
Speech synthesis technologies for individuals with vocal disabilities: Voice banking and reconstruction
TL;DR: The clinical applications of speech synthesis technologies are overviewed and a few selected researches are explained and the University of Edinburgh’s new project ‘‘Voice Banking and reconstruction’’ for patients with degenerative diseases, such as motor neurone disease and Parkinson's disease are introduced.
Improved Average-Voice-based Speech Synthesis Using Gender-Mixed Modeling and a Parameter Generation Algorithm Considering GV
Junichi Yamagishi,Takao Kobayashi,Stephen Renals,Simon King,Heiga Zen,Tomoki Toda,Keiichi Tokuda +6 more
TL;DR: This paper incorporates a high-quality speech vocoding method STRAIGHT and a parameter generation algorithm with global variance into the system for improving quality of synthetic speech and introduces a feature-space speaker adaptive training algorithm and a gender mixed modeling technique for conducting further normalization of the average voice model.
Patent
Enabling synthesis of speech having a target characteristic
TL;DR: In this article, a method involving: inputting target speech features derived from speech having a target characteristic; inputting labelling of the speech; and adapting, using a speech feature transform, statistical parameters of a predefined statistical parametric speech model to create an adapted SPMM configured to synthesize speech having the target characteristic.