Direct, modular and hybrid audio to visual speech conversion methods - a comparative study
نویسنده
چکیده
A systematic comparative study of audio to visual speech conversion methods is described in this paper. A direct conversion system is compared to conceptually different ASR based solutions. Hybrid versions of the different solutions will also be presented. The methods are tested using the same speech material, audio preprocessing and facial motion visualization units. Only the conversion blocks are changed. Subjective opinion score evaluation tests prove the naturalness of the direct conversion is the best.
منابع مشابه
Audio to visual speech conversion
In this thesis, I propose new results in audio speech based visual speech synthesis, which can be used as help for hard of hearing people or in computer aided animation. I will describe a synthesis tool which is based on direct conversion between audio and video modalities. I will discuss the properties of this system, measuring the speech quality and give solutions for occurrent drawbacks. I w...
متن کاملComparative Effect of Visual and Auditory Teaching Techniques on Retention of Word Stress patterns: A Case Study of English as a Foreign Language Curriculum in Iran
This study aimed at investigating the effect of visual (Cuisenaire Rods) and auditory nonsensical monosyllables using Pratt speech processing software as teaching techniques on retention of word stress. To this end, 60 high school participants made the two experimental groups of the study each having 30 students on the basis of their proficiency scores on KET (Key English Test). In one experime...
متن کاملA minimum converted trajectory error (MCTE) approach to high quality speech-to-lips conversion
High quality speech-to-lips conversion, investigated in this work, renders realistic lips movement (video) consistent with input speech (audio) without knowing its linguistic content. Instead of memoryless framebased conversion, we adopt maximum likelihood estimation of the visual parameter trajectories using an audio-visual joint Gaussian Mixture Model (GMM). We propose a minimum converted tra...
متن کاملReducing over-smoothness in HMM-based speech synthesis using exemplar-based voice conversion
Speech synthesis has been applied in many kinds of practical applications. Currently, state-of-the-art speech synthesis uses statistical methods based on hidden Markov model (HMM). Speech synthesized by statistical methods can be considered over-smooth caused by the averaging in statistical processing. In the literature, there have been many studies attempting to solve over-smoothness in speech...
متن کاملHydroponics Roofs for Saving Energy of Green Schools in the Cold and Dry climate of Iran: A Comparative Study between Two Broad and Modular Hydroponic Green Roofs
Green schools are a new type of school, in which the use of renewable energy is less than that of conventional schools. In this regard, nowadays, adding green layers to the roof of schools, in addition to increasing the Students' communication with nature, energy saving has improved in these spaces. However, to improve energy saving yield, the priority of these types of roofs in different clima...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2009