Simon King

Simon King

Auto-generated profile, based on publicly available information

Simon King

Centre for Speech Technology Research University of Edinburgh UK

Research Focus & Metrics

Academic Career Length

31Years (1996-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 November 2020 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Open access
BSBerrak Sisman
Berrak Sisman
JYJunichi Yamagishi
Junichi Yamagishi
SKSimon King
Simon King
HLHaizhou Li
Haizhou Li
Speaker identity is one of the important characteristics of human speech. In voice conversion, we change the speaker identity from one to another, while keeping the linguistic content unchanged. Voice conversion involves multiple speech processing techniques, such as speech analysis, spectral conversion, prosody conversion, speaker characterization, and vocoding. With the recent advances in theory and practice, we are now able to produce human-like voice quality with high speaker similarity. In this paper, we provide a comprehensive overview of the state-of-the-art of voice conversion techniques and their performance evaluation methods from the statistical approaches to deep learning, and discuss their promise and limitations. We will also report the recent Voice Conversion Challenges (VCC), the performance of the current state of technology, and provide a summary of the available resources for voice conversion research.

1 November 2013
Verified
Conference Paper
Closed access
CVChristophe Veaux
Christophe Veaux
JYJunichi Yamagishi
Junichi Yamagishi
SKSimon King
Simon King
The University of Edinburgh has started the development of a new speech database, the Voice Bank corpus, specifically designed for the creation of personalised synthetic voices for individuals with speech disorders. This corpus already constitutes the largest corpora of British English currently in existence, with more than 300 hours of recordings from approximately 500 healthy speakers. New recordings are continuously being made in order to get the best coverage of the different combinations of regional accents, social classes, age and gender across Britain. This paper describes the motivation and the processes involved in the design and recording of this corpus as well as some analysis of its content. The paper concludes with our future plans to further extend this corpus and to overcome its current limitations.

1 April 2015
Verified
Conference Paper
Closed access
ZWZhizheng Wu
Zhizheng Wu
CVCassia Valentini-Botinhao
Cassia Valentini-Botinhao
OWOliver Watts
Oliver Watts
SKSimon King
Simon King
Deep neural networks (DNNs) use a cascade of hidden representations to enable the learning of complex mappings from input to output features. They are able to learn the complex mapping from text-based linguistic features to speech acoustic features, and so perform text-to-speech synthesis. Recent results suggest that DNNs can produce more natural synthetic speech than conventional HMM-based statistical parametric systems. In this paper, we show that the hidden representation used within a DNN can be improved through the use of Multi-Task Learning, and that stacking multiple frames of hidden layer activations (stacked bottleneck features) also leads to improvements. Experimental results confirmed the effectiveness of the proposed methods, and in listening tests we find that stacked bottleneck features in particular offer a significant improvement over both a baseline DNN and a benchmark HMM system.

30 June 2009 in IEEE Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
JYJunichi Yamagishi
Junichi Yamagishi
TNTakashi Nose
Takashi Nose
HZHeiga Zen
Heiga Zen
ZLZhen-Hua Ling
Zhen-Hua Ling
TTTomoki Toda
Tomoki Toda
SRSteve Renals
Steve Renals
This paper describes a speaker-adaptive HMM-based speech synthesis system. The new system, called ldquoHTS-2007,rdquo employs speaker adaptation (CSMAPLR+MAP), feature-space adaptive training, mixed-gender modeling, and full-covariance modeling using CSMAPLR transforms, in addition to several other techniques that have proved effective in our previous systems. Subjective evaluation results show that the new system generates significantly better quality synthetic speech than speaker-dependent approaches with realistic amounts of speech data, and that it bears comparison with speaker-dependent approaches even when large amounts of speech data are available. In addition, a comparison study with several speech synthesis techniques shows the new system is very robust: It is able to build voices from less-than-ideal speech data and synthesize good-quality speech even for out-of-domain sentences.

1 October 2000 in Computer Speech & Language
Verified
Journal Article
Closed access
SKSimon King
Simon King
PTPaul Taylor
Paul Taylor

1 February 2007 in The Journal of the Acoustical Society of America
Verified
Journal Article
Closed access
PDF file
SKSimon King
Simon King
JFJoe Frankel
Joe Frankel
KLKaren Livescu
Karen Livescu
EMErik McDermott
Erik McDermott
KRKorin Richmond
Korin Richmond
MWMirjam Wester
Mirjam Wester
Although much is known about how speech is produced, and research into speech production has resulted in measured articulatory data, feature systems of different kinds, and numerous models, speech production knowledge is almost totally ignored in current mainstream approaches to automatic speech recognition. Representations of speech production allow simple explanations for many phenomena observed in speech which cannot be easily analyzed from either acoustic signal or phonetic transcription alone. In this article, a survey of a growing body of work in which such representations are used to improve automatic speech recognition is provided.