MASS: Multi-task anthropomorphic speech synthesis framework

Multi-lingual concatenative speech synthesis

This paper describes a method of concatenative speech synthesis that makes use of 3-dimensional labelling of speech, and shows how this can be applied to the synthesis of both mono-lingual and foreign-language speech. The dimensions encode phonetic, prosodic, and voicequality information in order to fully describe the acoustic characteristics of each speech segment.

A Probabilisti Framework for Multi-Task Learning

Fusion of multiple parameterisations for DNN-based sinusoidal speech synthesis with multi-task learning

It has recently been shown that deep neural networks (DNN) can improve the quality of statistical parametric speech synthesis (SPSS) when using a source-filter vocoder. Our own previous work has furthermore shown that a dynamic sinusoidal model (DSM) is also highly suited to DNN-based SPSS, whereby sinusoids may either be used themselves as a “direct parameterisation” (DIR), or they may be enco...

Bayesian speech synthesis framework integrating training and synthesis processes

This paper proposes a speech synthesis technique integrating training and synthesis processes based on the Bayesian framework. In the Bayesian speech synthesis, all processes are derived from one single predictive distribution which represents the problem of speech synthesis directly. However, it typically assumes that the posterior distribution of model parameters is independent of synthesis d...

A Graphbased Framework for Multi-Task Multi-View Learning

Many real-world problems exhibit dualheterogeneity. A single learning task might have features in multiple views (i.e., feature heterogeneity); multiple learning tasks might be related with each other through one or more shared views (i.e., task heterogeneity). Existing multi-task learning or multi-view learning algorithms only capture one type of heterogeneity. In this paper, we introduce Mult...