This paper introduces the speech synthesis system developed by USTC for Blizzard Challenge 2008. Two synthetic voices from the released UK English database are built using the HMMbased unit selection synthesis method, which is a hybrid of statistical parametric synthesis and unit-selection techniques. In this method, the optimal sequence of phone-sized candidate units is selected from the datab...

This paper addresses the use of speech alternatives to enrich speech synthesis systems. Speech alternatives denote the variety of strategies that a speaker can use to pronounce a sentence depending on pragmatic constraints, speaking style, and specific strategies of the speaker. During the training, symbolic and acoustic characteristics of a unit-selection speech synthesis system are statistica...

Abstract: Most synthesis techniques provide for some amount of parametric control. Generating suitable controls is a difficult problem, especially for instruments that admit continuous control by the performer. The traditional approach to control generation in computer music has been note-based, but note-by-note synthesis tends to overlook the interaction between notes in a phrase. This study c...

Environmental sounds present a difficult problem for sound modeling because spectral and temporal cues are tightly correlated. These sounds form classes that cannot be handled by traditional synthesis methods. Micro-level representations provide ways to control spectral and spatial cues in sound synthesis and meso-level representations determine the temporal structure of sound events. By constr...

This paper describes the application of the Harmonic plus Noise Model, HNM, for concatenative Text-to-Speech (TTS) synthesis. In the context of HNM, speech signals are represented as a time-varying harmonic component plus a modulated noise component. The decomposition of speech signal in these two components allows for more natural-sounding modi cations (e.g., source and lter modi cations) of t...

Parametric spatial audio coding methods aim to represent efficiently spatial information of recordings with psychoacoustically relevant parameters. In this study, it is presented how these parameters can be manipulated in various ways to achieve a series of spatial audio effects that modify the spatial distribution of a captured or synthesised sound scene, or alter the relation of its diffuse a...

This work presents an analytic solution to a 2-D waveguide mesh, made square with input and output at the center to produce a symmetry that reduces redundancy and increases computational savings. The result is a frequency-domain representation of the mesh, a parametric transfer function describing the ratio of output to input, symbolically computed to retain parameters. In this form, the mesh, ...

This paper studies the use of warped linear prediction (WLP) for wideband parametric speech synthesis. As the sampling frequency is increased from the usual 16 kHz, linear frequency resolution of conventional linear prediction (LP) cannot efficiently model the speech spectrum. By using frequency warping that weights perceptually the most important formant information, spectral models with bette...

A research project is presented in which we aim to design a speech synthesis model based on both the diphone and the allophone concepts, i.e. the data-driven and rule-driven approach for speech synthesis, respectively. At present, diphone concatenation for Dutch Ieads to more intelligible speech than when a rule-based allophone synthesis is applied, although the latter synthesis has the theoret...

We describe a continuous-pitch parametric vocoder suitable for speech coding and statistical text to speech synthesis. The spectral model is based on linear prediction. We show that glottal modelling techniques from recent literature can be cherry-picked to produce an excitation signal with properties known to be useful in the above application areas. We further show that the continuous pitch p...