Visualizing Speech Production with a Hidden Markov Model Tracker to Aid Speech Therapy and Communication by Pooja Jain Thesis

نویسندگان

  • Karrie G. Karahalios
  • Hyun Duk Cho
چکیده

Communication disorders occur across all age groups of people and often show first signs of appearing in children. These can range from problems in comprehension of speech to expression of speech to the point that it interferes with an individuals achievement and/or quality of life. Communication disorders can compromise a persons psychological, sociological, educational and vocational growth. There have been various studies on how the implications of these impairments can be mitigated through treatment, therapy and communication processes. This research focuses on the development and implementation of a software that aims to facilitate speech production by providing feedback through audio visualizations that represent basic audio features and coherent parts of speech tracked by a hidden Markov model. The goal of these visualizations is to help the user understand speech better by providing a system where users can see the words they speak and experience, develop and practice speech skills using the statistical speech model and temporal features represented through simple abstract visualizations. This research proposes an approach to visualize speech in a way that can potentially aid speech therapy and communication to help people with communication disorders by providing them with a tool they can use to understand their speech problems without the continuous need of a therapist or teacher.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Speech enhancement based on hidden Markov model using sparse code shrinkage

This paper presents a new hidden Markov model-based (HMM-based) speech enhancement framework based on the independent component analysis (ICA). We propose analytical procedures for training clean speech and noise models by the Baum re-estimation algorithm and present a Maximum a posterior (MAP) estimator based on Laplace-Gaussian (for clean speech and noise respectively) combination in the HMM ...

متن کامل

Improving Phoneme Sequence Recognition using Phoneme Duration Information in DNN-HSMM

Improving phoneme recognition has attracted the attention of many researchers due to its applications in various fields of speech processing. Recent research achievements show that using deep neural network (DNN) in speech recognition systems significantly improves the performance of these systems. There are two phases in DNN-based phoneme recognition systems including training and testing. Mos...

متن کامل

Iranian Speech -Language Pathologists’ Awareness of Alternative and Augmentative Communication Methods

Objectives: Alternative and Augmentative communication ( AAC ) provides a means of effective communication to persons with severe impairments in speech comprehension and production. The aim of this study was to examine the awareness of Iranian speech-language pathologists (SLPs) of AAC services. Methods:  A total of 111 SLPs who were selected by convenience sampling took part in this cross-sec...

متن کامل

ذخیره 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 2013