The Phase Substitutions in Czech Harmonic Concatenative Speech Synthesis

Tychtl, Z.; Matouš, Karel

doi:10.1007/978-3-540-39398-6_48

Cited by 2 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also due to its capability to manipulate the phase components during the synthesis. In [8] we proposed the method of "phase substitutions" which allows us to dramatically reduce the storage space of phase components in the harmonic AUI.…”

Section: Harmonic/noise-based Speech Productionmentioning

confidence: 99%

“…They are not only copies of the ones obtained by the analysis; during the off-line analysis, the starting candidate for the phase representative is selected from the spectrally stable part of the voiced segment in the unit and then it is extended by appending the additional elements to its end. The new elements are obtained by the analysis of the neighbouring frames in the analyzed segment [8]. The method stores only one phase vector for every uninterrupted voiced sequence of frames (voiced segment) instead of storing the phase vector for every frame.…”

Section: Harmonic/noise-based Speech Productionmentioning

confidence: 99%

See 1 more Smart Citation

Recent improvements on ARTIC: czech text-to-speech system

Matoušek¹,

Romportl²,

Tihelka³

et al. 2004

Interspeech 2004

View full text Add to dashboard Cite

This paper presents recent improvements on ARTIC -the modern Czech corpus-based text-to-speech system. As a statistical approach (using hidden Markov models) was applied to create an acoustic unit inventory, several improvements concerning acoustic unit modelling, clustering and segmentation have been accomplished to increase the intelligibility of the resulting speech. Two approaches to the generation of prosodic features were also proposed and implemented to increase the naturalness of synthetic speech. To produce as smooth synthetic speech as possible, a multiple unit instance scheme with on-line unit candidate selection was proposed as well. Our work on an alternative harmonic/noise-based speech production method is also mentioned. In addition, an important step towards multilinguality was achieved as German and Slovak language modules were implemented besides two Czech voices within the framework of ARTIC TTS system.

show abstract

Section: Harmonic/noise-based Speech Productionmentioning

confidence: 99%

Section: Harmonic/noise-based Speech Productionmentioning

confidence: 99%

Recent improvements on ARTIC: czech text-to-speech system

Matoušek¹,

Romportl²,

Tihelka³

et al. 2004

Interspeech 2004

View full text Add to dashboard Cite

show abstract

“…In fact, all standard concatenative techniques can be used in the system. OLA-like [1] and harmonic/noise-based (HNM) [7] synthesis methods have been implemented in the system so far. These methods use so-called pitch-marks, glottal closure instances (detected from glottal signals [2]), to change the prosodic characteristics of synthesized speech.…”

Section: Text-to-speechmentioning

confidence: 99%

Slovak Text-to-Speech Synthesis in ARTIC System

Matoušek

Tihelka

2004

Text, Speech and Dialogue

View full text Add to dashboard Cite

Abstract. This paper presents a brand-new Slovak text-to-speech system. It was developed within the framework of ARTIC system (primarily designed to synthesize Czech speech) with respect to the knowledge of Slovak language. Thus, statistical approach (using hidden Markov models) was employed to build an acoustic unit inventory of Slovak language in a fully automatic way. Both phonetic transcription and prosodic rules were proposed to convert an input text to its phonetic form and to estimate its suprasegmental features. As a result, a fully working text-tospeech system that converts an arbitrary Slovak text to the corresponding output speech was designed. The informal listening tests show the system is capable of producing speech of a high quality (with high level of intelligibility and good naturalness).

show abstract

The Phase Substitutions in Czech Harmonic Concatenative Speech Synthesis

Cited by 2 publications

References 3 publications

Recent improvements on ARTIC: czech text-to-speech system

Recent improvements on ARTIC: czech text-to-speech system

Slovak Text-to-Speech Synthesis in ARTIC System

Contact Info

Product

Resources

About