machine learning and its application to speech impediment therapy

12
Project Data Title: Machine Learning and its Application to Speech Impediment Therapy Duration: February 2002 - February 2004 www: <http://oasis.inf.u- szeged.hu/speechmaster> Grant No.: IKTA4-055/2001 Keywords: artificial intelligence, machine learning, real-time phoneme recognition, teaching of reading,

Upload: kathy-parr

Post on 01-Apr-2015

226 views

Category:

Documents


2 download

TRANSCRIPT

Page 1: Machine Learning and its Application to Speech Impediment Therapy

Project Data

Title: Machine Learning and its Application to Speech Impediment Therapy

Duration: February 2002 - February 2004www: <http://oasis.inf.u-szeged.hu/speechmaster>Grant No.: IKTA4-055/2001Keywords: artificial intelligence, machine learning, real-time phoneme recognition, teaching of reading, speech impediment therapy

Page 2: Machine Learning and its Application to Speech Impediment Therapy

Project members:Co-ordinator:

University of Szeged,Department of InformaticsAddress: H-6720, Szeged, Árpád tér 2. Project/team leader: András Kocsor

Consortium members:

University of Szeged, Training Teaching School, Team leader: János Bácsi,

Kindergarten, Primary school and Boarding school,(the school for the deaf) Team leader: Jenő Mihalovics,

Page 3: Machine Learning and its Application to Speech Impediment Therapy

SummaryThe project consists of two main parts:

a research part and an application part.

The research part is devoted to investigating modern machine learning techniques which can form the basis of the development of several info-communication systems. The machine learning algorithms developed have been made available as open-source software.

One example of these applications is speech recognition, which is the heart of the “SpeechMaster” software, developed in the second, application part of our project.

Page 4: Machine Learning and its Application to Speech Impediment Therapy

Machine Learning Algorithms

Basic assumptions:a) objects are characterized by featuresb) each feature constitutes one dimension in the feature space

Questions:- concept making- classification- feature selection- feature space transformation- dimension reduction

99%

Page 5: Machine Learning and its Application to Speech Impediment Therapy

Linear feature space transformations:

- Principal Component Analysis

- Independent Component Analysis

- Linear Discriminant Analysis

- Springy Discriminant Analysis

Machine Learning Algorithms99%

Page 6: Machine Learning and its Application to Speech Impediment Therapy

Machine Learning AlgorithmsNonlinear feature space transformations:

- Kernel Principal Component Analysis

- Kernel Independent Component Analysis

- Kernel Linear Discriminant Analysis

- Kernel Springy Discriminant Analysis

99%

Page 7: Machine Learning and its Application to Speech Impediment Therapy

99% Machine Learning AlgorithmsMachine learning algorithms:

- Artificial Neural Nets

- Gaussian Mixture Modeling

- Support Vector Machines

- Projection Pursuit Learner

Page 8: Machine Learning and its Application to Speech Impediment Therapy

a) real-time phoneme recognition

b) word recognition

Speech Recognition70%

Methods:

- machine learning

- speech corpora

Page 9: Machine Learning and its Application to Speech Impediment Therapy

Speech Corpora

200 speakers of different ages

• 500 speakers(male/female 50-50%)

• age: 6-7

Speech impediment therapy Teaching of reading

90%

Page 10: Machine Learning and its Application to Speech Impediment Therapy

The “SpeechMaster”60%

Phonological Awareness Teaching

Page 11: Machine Learning and its Application to Speech Impediment Therapy

The “SpeechMaster”60%

Phoneme-Grapheme association

Page 12: Machine Learning and its Application to Speech Impediment Therapy

The “SpeechMaster”60%

Visual feedback for the hearing impaired