International audienceUnit selection speech synthesis systems rely, except for rare cases, on target and concaténation costs for selecting the best unit sequence. The role of the concatenation cost is to insure that joining two voice segments will not cause any acoustic artefact to appear. For this task, acoustic distances (MFCC, F0) are typically used but in many cases, this is not enough. In this paper, we introduce a penalty in the concaténation cost, inherited from the field of corpus covering, in order to block some concaténations based on their phonological class. Moreover, a derived fuzzy version is proposed to relax the penalty based on the concaténation quality with respect to the cost distribution. An objective evaluation showed t...
Concatenating units of natural speech is one method of speech synthesis1. Most such systems use an i...
International audienceWhen trying to assess the effectiveness of a new speech synthesis method, rese...
In this paper, we present a novel statistical approach to corpus-based speech synthesis. Classically...
International audienceUnit selection speech synthesis systems rely, except for rare cases, on target...
International audienceUnit selection speech synthesis systems generally rely on target and concatena...
This PhD thesis focuses on the automatic speech synthesis field, and more specifically on unit selec...
For concatenative speech synthesis based on non-uniform unit selection, the key to improve the synth...
This thesis relates to text-to-speech synthesis and deals more particularly with the corpus based ap...
In our previous papers, we have proposed join cost functions derived from spectral distances, which ...
Undoubtedly, state-of-the-art unit selection-based concatenative speech systems produce very high qu...
In concatenative text-to-speech (TTS) synthesis systems unit selection aims to reduce the number of ...
Undoubtedly, state-of-the-art unit selection-based concatenative speech systems produce very high qu...
ICASSP2003: IEEE International Conference on Acoustics, Speech, and Signal Processing, April 6-10,...
In our previous papers, we have proposed join cost functions derived from spectral distances, which ...
In unit selection-based concatenative speech synthesis, join cost (also known as concatenation cost)...
Concatenating units of natural speech is one method of speech synthesis1. Most such systems use an i...
International audienceWhen trying to assess the effectiveness of a new speech synthesis method, rese...
In this paper, we present a novel statistical approach to corpus-based speech synthesis. Classically...
International audienceUnit selection speech synthesis systems rely, except for rare cases, on target...
International audienceUnit selection speech synthesis systems generally rely on target and concatena...
This PhD thesis focuses on the automatic speech synthesis field, and more specifically on unit selec...
For concatenative speech synthesis based on non-uniform unit selection, the key to improve the synth...
This thesis relates to text-to-speech synthesis and deals more particularly with the corpus based ap...
In our previous papers, we have proposed join cost functions derived from spectral distances, which ...
Undoubtedly, state-of-the-art unit selection-based concatenative speech systems produce very high qu...
In concatenative text-to-speech (TTS) synthesis systems unit selection aims to reduce the number of ...
Undoubtedly, state-of-the-art unit selection-based concatenative speech systems produce very high qu...
ICASSP2003: IEEE International Conference on Acoustics, Speech, and Signal Processing, April 6-10,...
In our previous papers, we have proposed join cost functions derived from spectral distances, which ...
In unit selection-based concatenative speech synthesis, join cost (also known as concatenation cost)...
Concatenating units of natural speech is one method of speech synthesis1. Most such systems use an i...
International audienceWhen trying to assess the effectiveness of a new speech synthesis method, rese...
In this paper, we present a novel statistical approach to corpus-based speech synthesis. Classically...