Speech Feature Computations for Visual Speech Articulation Training
نویسندگان
چکیده
SPEECH FEATURE COMPUTATIONS FOR VISUAL SPEECH ARTICULATION TRAINING Stefan Auberg Old Dominion University, 1996 Director: Dr. Stephen A. Zahorian A new version of the Visual Speech Articulation Training Aid was implemented which provides real-time visual feedback for speech articulation training. This version was migrated to a Windows Multimedia PC from a previous version which used a Personal Computer (PC) system and additional specialized and expensive custom hardware. This new version will make the system more available to schools and private users. A new method was developed for computing spectral/temporal features which characterize the speech sounds. In addition to the typical frame-based spectral analysis parameters, the new method represents temporal changes of the spectrum with a small number of features. The flexible method implemented can easily be adapted to compute features for a wide range of speech processing tasks. Linguistically-based distinctive features were also investigated as candidate features for the visual display system. Some experimental results are given for vowels using the new system. SPEECH FEATURE COMPUTATION FOR VISUAL SPEECH ARTICULATION TRAINING
منابع مشابه
Comparison of Motor Skills Among Studens with Intellectual Disability, Stuttering, Articulation Problems and Normal Speech
Objective: This research aimed to compare the motor skills among students with intellectual disability, stuttering, articulation problems and normal speech. Methods: The study was a retrospective causal-comparative research. From among all elementary male students with intellectual disability in Urmia city, 90 students (30 students in each group) were selected. All groups completed the revised ...
متن کاملAudio-Visual Speech Recognition for a Person with Severe Hearing Loss Using Deep Canonical Correlation Analysis
Recently, we proposed an audio-visual speech recognition system based on a neural network for a person with an articulation disorder resulting from severe hearing loss. In the case of a person with this type of articulation disorder, the speech style is quite different from that of people without hearing loss, making a speaker-independent acoustic model for unimpaired persons more or less usele...
متن کاملAudio-Visual Speech Recognition Using Bimodal-Trained Bottleneck Features for a Person with Severe Hearing Loss
In this paper, we propose an audio-visual speech recognition system for a person with an articulation disorder resulting from severe hearing loss. In the case of a person with this type of articulation disorder, the speech style is quite different from those of people without hearing loss that a speaker-independent acoustic model for unimpaired persons is hardly useful for recognizing it. The a...
متن کاملInnovations in Czech audio-visual speech synthesis for precise articulation
This paper presents new steps toward animation of precise articulation. The acquisition of audio-visual corpus for Czech and new method for parameterization of visual speech was designed to obtain exact speech data. The parameterization method is primarily suitable for training a data driven visual speech synthesis systems. The audio-visual corpus includes also specially designed test part. Fur...
متن کاملSpeech and Reading Disorders Screening, and Problems in Structure and Function of Articulation Organs in Children in Mashhad City, Iran
Background and Objectives: Investigating the prevalence of speech and language disorders and the contributing factors can help determine the best treatment options suited to the needs of these patients. So far, no comprehensive study has been conducted on screening speech and reading disorders and problems in the structure and function of articulation organs (PSFAOs) in children in Mashhad City...
متن کامل