نتایج جستجو برای: naturalness

تعداد نتایج: 2801  

2004
Yves Bontemps Patrick Heymans Pierre-Yves Schobbens Jean-Christophe Trigaux

Extended Feature Oriented Domain Analysis (FODA) Feature Diagrams (EFD) were introduced to compensate for a purported ambiguity and lack of precision and expressiveness of the original FODA feature diagrams (OFD). However, EFD never received a formal semantics, which is the hallmark of precision and unambiguity. We propose here a semantics for both diagrams. From this we demonstrate that OFD ar...

2012
Elizabeth R. Cole Lanice R. Avery Catherine Dodson Kevin D. Goodman

This article examines the public debate over marriage law to investigate how arguments based on claims about what is natural privilege some relationships while stigmatizing others and justifying discriminatory policies toward sexual minorities. Articles about same-sex marriage appearing in major newspapers were content-coded according to absence or presence of four dimensions of naturalness: ch...

2000
Richard Ogden Sarah Hawkins Jill House Mark Huckvale John Local Paul Carter Jana Dankovičová Sebastian Heid

This paper outlines ProSynth, an approach to speech synthesis which takes a rich linguistic structure as central to the generation of natural-sounding speech. We start from the assumption that the acoustic richness of the speech signal reflects linguistic structural richness and underlies the percept of naturalness. Naturalness achieved by paying attention to systematic phonetic detail in the s...

2012
Smita Kawachale J. S. Chitode

This paper presents methods for automatic speech signal segmentation using neural network. Speech signal segmentation is carried out to form syllables. Syllable is a common unit for concatenative TTS systems. Concatenative TTS being using speech segments of recorded speech is natural as compare to Formant or Articulatory TTS systems. This TTS stores small segments of speech and join them togeth...

1999
J. A. Casas J. R. Espinosa A. Ibarra I. Navarro

If neutrinos are to play a relevant cosmological role, they must be essentially degenerate. We study whether radiative corrections can or cannot be responsible for the small mass splittings, in agreement with all the available experimental data. We perform an exhaustive exploration of the bimaximal mixing scenario, finding that (i) the vacuum oscillations solution to the solar neutrino problem ...

1999
Robert B. Pippin

The problem of freedom in modern philosophy has three basic components: (i) what is freedom, or what would it be to act freely? (ii) Is it possible so to act? (iii) And how important is leading a free life?1 Hegel proposed unprecedented and highly controversial answers to these questions. (i) What we want to be able to explain when we ask ‘what is freedom?’ are the conditions that must be fulfi...

1999
G. L. Kane S. F. King

We analyse the fine-tuning constraints arising from absence of superpartners at LEP, without strong universality assumptions. We show that such constraints do not imply that charginos or neutralinos should have been seen at LEP, contrary to the usual arguments. They do however imply relatively light gluinos (

2014
Kou Tanaka Tomoki Toda Graham Neubig Sakriani Sakti Satoshi Nakamura

An electrolarynx is a device that artificially generates excitation sounds to produce electrolaryngeal (EL) speech. Although proficient laryngectomees can produce intelligible EL speech by using this device, it sounds quite unnatural due to the mechanical excitation. To address this issue, we have proposed several EL speech enhancement methods using statistical voice conversion and showed that ...

2011
Cyril Auran Caroline Bouzon

This paper details two perception experiments based on synthetic British English obtained with CART models predicting phone durations in slow speech from normal speed speech. Speech rate and naturalness were assessed by 6 English natives. Synthetic slow speech was rated as both slower and less natural than natural slow speech; however, the insertion of the pauses produced in natural slow speech...

2007
Jordi Adell Antonio Bonafonte David Escudero Mancebo

Speech synthesis techniques have already reached a high level of naturalness. However, they are often evaluated on text reading tasks. New applications will request for conversational speech instead and disfluencies are crucial in such a style. The present paper presents a system to predict filled pauses and synthesise them. Objective results show that they can be inserted with 96% precision an...

نمودار تعداد نتایج جستجو در هر سال

با کلیک روی نمودار نتایج را به سال انتشار فیلتر کنید