activity
20182020
most citedTraditional Machine Learning for Pitch Detection

32 citations · 64 across the 4 of their papers we have counts for

collaborators

6 papers

eess.AS20201 cited

Glottal source estimation robustness: A comparison of sensitivity of voice source estimation techniques

Thomas Drugman, Thomas Dubuisson, Alexis Moinet +2

This paper addresses the problem of estimating the voice source directly from speech waveforms. A novel principle based on Anticausality Dominated Regions (ACDR) is used to estimat…

cs.SD202031 cited

Voice Conversion for Whispered Speech Synthesis

Marius Cotescu, Thomas Drugman, Goeric Huybrechts +2

We present an approach to synthesize whisper by applying a handcrafted signal processing recipe and Voice Conversion (VC) techniques to convert normally phonated speech to whispere…

cs.SD2019

Using a Pitch-Synchronous Residual Codebook for Hybrid HMM/Frame Selection Speech Synthesis

Thomas Drugman, Alexis Moinet, Thierry Dutoit +1

This paper proposes a method to improve the quality delivered by statistical parametric speech synthesizers. For this, we use a codebook of pitch-synchronous residual frames, so as…

eess.AS2019

Singing Synthesis: with a little help from my attention

Orazio Angelini, Alexis Moinet, Kayoko Yanagisawa +1

We present UTACO, a singing synthesis model based on an attention-based sequence-to-sequence mechanism and a vocoder based on dilated causal convolutions. These two classes of mode…

cs.SD201932 cited

Traditional Machine Learning for Pitch Detection

Thomas Drugman, Goeric Huybrechts, Viacheslav Klimkov +1

Pitch detection is a fundamental problem in speech processing as F0 is used in a large number of applications. Recent articles have proposed deep learning for robust pitch tracking…

eess.AS2018

Comprehensive evaluation of statistical speech waveform synthesis

Thomas Merritt, Bartosz Putrycz, Adam Nadolski +10

Statistical TTS systems that directly predict the speech waveform have recently reported improvements in synthesis quality. This investigation evaluates Amazon's statistical speech…