Voice Quality Modelling for Expressive Speech Synthesis
نویسندگان
چکیده
منابع مشابه
Voice Quality Modelling for Expressive Speech Synthesis
This paper presents the perceptual experiments that were carried out in order to validate the methodology of transforming expressive speech styles using voice quality (VoQ) parameters modelling, along with the well-known prosody (F 0, duration, and energy), from a neutral style into a number of expressive ones. The main goal was to validate the usefulness of VoQ in the enhancement of expressive...
متن کاملExperiments with voice modelling in speech synthesis
Some experiments with voice modelling using reccnl dcvelopmcnts of the KTH spccch synthesis systcm will bc presented. The ncw synthesizer, GLOVE, is an extended version of OVE 111. I t contains an improved glottal source built on the LF-model and some extra conlrol parameters for the voiced and noise sources and an extra polc/zcro-pair in the nasal branch. Furthcrrnorc, thc present rcscarch ver...
متن کاملExpressive Speech Synthesis: Evaluation of a Voice Quality Centered Coder on the Different Acoustic Dimensions
Expressive speech is intrinsically multi-dimensional. Each acoustic dimension has specific weights depending on the nature of the expressed affects. The quantity of expressive information carried by each dimension separately (using Praat algorithms), as well as the processing implied to carry it (global value vs. contour) has been perceptively measured for a set of natural mono-syllabic utteran...
متن کاملAutomatic labelling of voice-quality in speech databases for synthesis
A series of experiments was performed to determine the extent to which voice-quality di erences could be labelled automatically in a speech database. Using speech corpora of three di erent speaking styles from the same speaker as test material, hidden-Markov models were trained to distinguish the prosodic and acoustic characteristics of each style, and were used to re-label the voiced-segments ...
متن کاملVoice quality interpolation for emotional text-to-speech synthesis
Synthesizing desired emotions using concatenative algorithms relies on collection of large databases. This paper focuses on the development and assessment of a simple algorithm to interpolate the intended vocal effort in existing databases in order to create new databases with intermediate levels of vocal effort. Three diphone databases in German with soft, modal, and loud voice qualities are p...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Scientific World Journal
سال: 2014
ISSN: 2356-6140,1537-744X
DOI: 10.1155/2014/627189