Optimal Coupling of Diphones

Text-to-speech conversion has traditionally been performed either by concatenating short samples of speech or by using rule-based systems to convert a phonetic representation of speech into an acoustic representation, which is then converted into speech. This paper describes a text-to-speech synthesis system for modern standard Arabic based on artificial neural networks and residual excited LPC coder. The networks offer a storage-efficient means of synthesis without the need for explicit rule enumeration. These neural networks require large prosodically labeled continuous speech databases in their training stage. As such databases are not available for the Arabic language, we have developed one for this purpose. Thus, we discuss various stages undertaken for this development process. In addition to interpolation capabilities of neural networks, a linear interpolation of the coder parameters is performed to create smooth transitions at segment boundaries. A residual-excited all pole vocal tract model and a prosodic-information synthesizer based on neural networks are also described in this paper.

show abstract

“…We can also use this measure for optimal coupling [34]. This means we can also find the best place to join the two units.…”

Section: Unit Selection-based Synthesizer For Comparisonmentioning

confidence: 97%

Towards a high quality Arabic speech synthesis system based on neural networks and residual excited vocal tract model

Chouireb

Guerti

2007

SIViP

View full text Add to dashboard Cite

show abstract

“…With this in mind, it seems that there is little value in developing methods for high precision placement of phone boundaries. Techniques such as optimal coupling (Conkie and Isard, 1996) can adjust the actual cut points at synthesis time (typically by minimising the local join cost, after the unit sequence has been selected), compensating for some inaccuracy in label placement.…”

Section: Automatic Segmentation Techniquesmentioning

confidence: 99%

Multisyn: Open-domain unit selection for the Festival speech synthesis system

Clark

Richmond²,

King³

2007

Speech Communication

113

View full text Add to dashboard Cite

“…In order to further enhance the concatenation quality, we designed an optimization method that selects the best cut-markers according to a MEL-scale spectral distance, as suggested in [17]. This technique selects for each join a pitch marker from the first and from the second segment in such a way that the transition will occur where there is as much similarity between the two speech signals as possible.…”

Section: Segment Concatenationmentioning

confidence: 99%

Expressive Speech Recognition and Synthesis as Enabling Technologies for Affective Robot-Child Communication

Yilmazyildiz

Mattheyses

Patsis

et al. 2006

Advances in Multimedia Information Processing - PCM 2006

View full text Add to dashboard Cite

Abstract. This paper presents our recent and current work on expressive speech synthesis and recognition as enabling technologies for affective robot-child interaction. We show that current expression recognition systems could be used to discriminate between several archetypical emotions, but also that the old adage "there's no data like more data" is more than ever valid in this field. A new speech synthesizer was developed that is capable of high quality concatenative synthesis. This system will be used in the robot to synthesize expressive nonsense speech by using prosody transplantation and a recorded database with expressive speech examples. With these enabling components lining up, we are getting ready to start experiments towards hopefully effective child-machine communication of affect and emotion.

show abstract

Optimal Coupling of Diphones

Cited by 32 publications

References 6 publications

Towards a high quality Arabic speech synthesis system based on neural networks and residual excited vocal tract model

Towards a high quality Arabic speech synthesis system based on neural networks and residual excited vocal tract model

Multisyn: Open-domain unit selection for the Festival speech synthesis system

Expressive Speech Recognition and Synthesis as Enabling Technologies for Affective Robot-Child Communication

Contact Info

Product

Resources

About