Continuous probabilistic transform for voice conversion
- Y. Stylianou, O. Cappé, É. Moulines
- Computer ScienceIEEE Transactions on Speech and Audio Processing
- 1 March 1998
The design of a new methodology for representing the relationship between two sets of spectral envelopes and the proposed transform greatly improves the quality and naturalness of the converted speech signals compared with previous proposed conversion methods.
Harmonic plus noise models for speech, combined with statistical methods, for speech and speaker modification
- Y. Stylianou
Applying the harmonic plus noise model in concatenative speech synthesis
- Y. Stylianou
- PhysicsIEEE Transactions on Speech and Audio Processing
The harmonic plus noise model (HNM) for concatenative text-to-speech (TTS) synthesis provides high-quality speech synthesis while outperforming other models for synthesis (e.g., TD-PSOLA) in intelligibility, naturalness, and pleasantness.
Bird detection in audio: A survey and a challenge
- D. Stowell, Mike Wood, Y. Stylianou, H. Glotin
- Computer ScienceInternational Workshop on Machine Learning for…
- 11 August 2016
New datasets and an IEEE research challenge are introduced to make possible the development of fully automatic algorithms for bird sound detection, and identify a widespread need for tuning-free and species-agnostic approaches.
Automatic acoustic detection of birds through deep learning: The first Bird Audio Detection challenge
- D. Stowell, Y. Stylianou, Mike Wood, H. Pamula, H. Glotin
- Computer ScienceMethods in Ecology and Evolution
- 16 July 2018
Results from a collaborative data challenge showed that general‐purpose acoustic bird detection can achieve very high retrieval rates in remote monitoring data, with no manual recalibration, and no pretraining of the detector for the target species or the acoustic conditions in the target environment.
The AT & T NEXT-GEN TTS system
The new AT&T TTS system for general U.S. English text is based on best‐choice components picked from the AT&T Flextalk TTS, the Festival System from the University of Edinburgh, and ATR’s CHATR…
PROCEDURE AND TEST OF AN INTERNAL DRAINAGE METHOD FOR MEASURING SOIL HYDRAULIC CHARACTERISTICS IN SITU
Speech-in-noise intelligibility improvement based on spectral shaping and dynamic range compression
Experiments with speech shaped (SSN) and competing speaker types of noise at various low SNR values show that the suggested approach outperforms state-of-the art methods in terms of the Speech Intelligibility Index (SII).
Statistical methods for voice quality transformation
Voice Pathology Detection and Discrimination Based on Modulation Spectral Features
- M. Markaki, Y. Stylianou
- Computer ScienceIEEE Transactions on Audio, Speech, and Language…
- 1 September 2011
The information provided by a joint acoustic and modulation frequency representation, referred to as modulation spectrum, for detection and discrimination of voice disorders is explored and the suggested approach significantly outperformed the performance of cepstral-based features.