Fewer con- catenations and less signal processing enable large corpus TTS systems to produce smoother and more natural sounding syn- thetic speech. Recent ...

Bibliographic details on Perceptual cost functions for unit searching in large corpus-based text-to-speech.

We also propose a new method for setting weights in the cost functions based on a perceptual preference test. Our results show that this approach can ...

This paper describes a new corpus-based Bell Labs' TTS system that encompasses large acoustic inventories with a rich set of annotations, models and data ...

This paper proposes a method for tuning the weights of unit selection cost functions in syllable based text-to-speech (TTS) synthesis system.

This paper describes optimizing a cost function for segment selection in concatenative Text-to-Speech based on perceptual characteristics.

In this work, we attempt to identify the priorities for different features and try to optimize the unit selection with perceptual clustering. Out approach first ...

We present a novel concept to increase the efficiency of the exhaustive speech unit search within the database by an unit selection model, which is based on ...

Nov 30, 2020 · A new, fully interpretable fuzzy unit selection cost function. A new objective measure for optimizing a fuzzy unit selection cost function.

This paper presents the design and development of syllable specific unit selection cost functions for improving the quality of text-to-speech synthesis.