What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Machine learning
Yannis Stylianou spends much of his time researching Speech recognition, Speech synthesis, Speech processing, Artificial intelligence and Intelligibility.
The Speech recognition study combines topics in areas such as Noise, Selection and Signal processing.
His work on Speech technology as part of general Speech synthesis research is often related to Noise figure, thus linking different fields of science.
His Speech processing research integrates issues from Mixture model and Time–frequency analysis.
The concepts of his Artificial intelligence study are interwoven with issues in Machine learning and Pattern recognition.
His Intelligibility research is multidisciplinary, incorporating elements of Smoothing and Noise component.
His most cited work include:
- Continuous probabilistic transform for voice conversion (828 citations)
- Applying the harmonic plus noise model in concatenative speech synthesis (306 citations)
- Harmonic plus noise models for speech, combined with statistical methods, for speech and speaker modification (217 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Speech recognition, Artificial intelligence, Speech synthesis, Speech processing and Intelligibility.
His Speech recognition study combines topics from a wide range of disciplines, such as Speech enhancement and Noise.
Yannis Stylianou combines subjects such as Machine learning and Pattern recognition with his study of Artificial intelligence.
As a part of the same scientific study, Yannis Stylianou usually deals with the Speech synthesis, concentrating on Harmonic and frequently concerns with Harmonic analysis.
In the subject of general Speech processing, his work in Speech technology is often linked to Gaussian process, thereby combining diverse domains of study.
His work deals with themes such as Smoothing, Spectral shaping, Loudness and Dynamic range compression, which intersect with Intelligibility.
He most often published in these fields:
- Speech recognition (74.68%)
- Artificial intelligence (27.85%)
- Speech synthesis (22.78%)
What were the highlights of his more recent work (between 2017-2020)?
- Speech recognition (74.68%)
- Artificial intelligence (27.85%)
- Intelligibility (20.68%)
In recent papers he was focusing on the following fields of study:
Yannis Stylianou mainly focuses on Speech recognition, Artificial intelligence, Intelligibility, Speech synthesis and Speech enhancement.
His study in the field of Hidden Markov model also crosses realms of Parametric statistics.
His study in Intelligibility is interdisciplinary in nature, drawing from both Spectral shaping, Auditory processing disorder, Loudness and Speech processing.
His Speech synthesis research focuses on subjects like Adaptation, which are linked to Expression and Similarity.
As part of the same scientific family, Yannis Stylianou usually focuses on Speech enhancement, concentrating on Background noise and intersecting with Mutual information, Voice activity detection, Word error rate and Classifier.
His studies in Noise integrate themes in fields like Channel and Context.
Between 2017 and 2020, his most popular works were:
- Automatic acoustic detection of birds through deep learning: The first Bird Audio Detection challenge (61 citations)
- A study of time-frequency features for CNN-based automatic heart sound classification for pathology detection. (45 citations)
- ON the Use of Wavenet as a Statistical Vocoder (40 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algebra
His scientific interests lie mostly in Artificial intelligence, Deep learning, Speech recognition, Multi domain and Multiple Models.
His research integrates issues of Passive acoustic monitoring and Pattern recognition in his study of Artificial intelligence.
His Deep learning study frequently links to adjacent areas such as Robustness.
His Speech recognition research is multidisciplinary, incorporating perspectives in Training set and Adaptation.
His Multi domain research incorporates Single model, Dialogue management, Scalability and Domain.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
