Low-dimensional parameter mapping using spectral envelopes
نویسنده
چکیده
We explore the technique of controlling synthesis using an instrumental or other sound source. The range of spectra available from the sound source, and also that available from the synthesis technique, are estimated and the first is mapped to the second. Suitable synthesis parameters for the synthesis algorithms are found by searching a database of known output spectra. A simple experiment illustrates the technique.
منابع مشابه
Voice conversion using generative trained deep neural networks with multiple frame spectral envelopes
This paper presents a deep neural network (DNN) based spectral envelope conversion method. A global DNN is employed to model the complex non-linear mapping relationship between the spectral envelopes of source and target speakers. The proposed DNN is generatively trained layer-by-layer by cascade of two restricted Boltzmann machines (RBMs) and a bidirectional associative memory (BAM), which are...
متن کاملMapping spatial variability of soil salinity in a coastal area located in an arid environment using geostatistical and correlation methods based on the satellite data
Saline lakes can increase the soil and water salinity of the coastal areas. The main aim of this study is to distinguish the characteristics of the spectral reflectance of saline soil, analyze the statistical relationship between soil EC and characteristics of the spectral reflectance of saline soil, and to map soil salinity east of the Maharloo Lake. The correlation between field measurements ...
متن کاملEstimating detailed spectral envelopes using articulatory clustering
This paper presents an articulatory-acoustic mapping where detailed spectral envelopes are estimated. During the estimation, the harmonics of a range of values are derived from the spectra of multiple voiced speech signals vocalized with similar articulator settings. The envelope formed by these harmonics is represented by a cepstrum, which is computed by fitting the peaks of all the harmonics ...
متن کاملA Spectral Gamut-Mapping Environment with Rendering Parameter Feedback
This paper proposes a prototypical environment for gamut mapping in spectral space. Images are rendered in terms of light and material parameters by a symbolic ray tracer, and the parameter ranges are adjusted, without re-rendering, to bring the image into the output device’s spectral gamut. There is a growing disparity between the high dynamic range images produced by spectral renderers and th...
متن کاملAccurate spectral envelope estimation for articulation-to-speech synthesis
This paper introduces a novel articulatory-acoustic mapping in which detailed spectral envelopes are estimated based on the cepstrum, inclusive of the high-quefrency elements which are discarded in conventional speech synthesis to eliminate the pitch component of speech. For this estimation, the method deals with the harmonics of multiple voiced-speech spectra so that several sets of harmonics ...
متن کامل