5 accepted papers
Many modern neural networks use histograms to efficiently model continuous random variables. This implies that the parametric space of the multinomial distribution is easier for training large neural networks. In applications like generative audio networks, this approach introduces audible quantizat…
This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a voc…
This paper presents a mathematical framework that is suitable for voice conversion and adaptation in speech processing. Voice conversion is formulated as a search for the optimal correspondances between a set of source-speaker spectra and a set of target-speaker spectra under a transform that compen…
Dynamic Frequency Warping (DFW) is widely used to align spectra of different speakers. It has long been argued that frequency warping captures inter-speaker differences but DFW practice always involves a tricky preprocessing part to remove spectral tilt. The DFW residual is successfully used in Voic…
Vocoders received renewed attention recently as basic components in speech synthesis applications such as voice transformation, voice conversion and statistical parametric speech synthesis. This paper presents a new vocoder synthesizer, referred to as Vocaine, that features a novel Amplitude Modulat…