Dysarthria is a neuromuscular disorder, occurs due to improper coordination of speech musculature. In order to improve the quality of life of people with speech disorder, assistive technology using automatic speech recognition (ASR) systems are gaining importance. Since it is difficult for dysarthric speakers to provide sufficient data, data insufficiency is one of the major problems in building an efficient dysarthric ASR system. In this paper, we focus on handling this issue by pooling data from unimpaired speech database. Then feature space maximum likelihood linear regression (fMLLR) transformation is applied on pooled data and dysarthric data to normalize the effect of inter-speaker variability. The acoustic model built using the combined features (acoustically transformed dysarthric + pooled features) gives an relative improvement of 18.09% and 50.00% over baseline system for Nemours database and Universal Access speech (digit set) database. © 2015 IEEE.

Srinivasan Umesh

Department of Electrical Engineering

M Ramasubba Reddy

Department of Applied Mechanics

Database systems

Linear transformations

Mathematical transformations

Maximum likelihood

Metadata

Speech

Assistive technology

Automatic speech recognition system

DATA INSUFFICIENCY

DATA POOLING

FMLLR

MAXIMUM LIKELIHOOD LINEAR REGRESSION

NEUROMUSCULAR DISORDERS

SPEAKER VARIABILITY

Speech Recognition

IIT Madras is a public technical and research university located in Chennai, Tamil Nadu. Founded in 1959, it is recognised as an Institute of National Importance.

IIT Madras has been ranked as the top engineering institute in India for four years in a row by the National Institutional Ranking Framework of the MHRD

It currently offers undergraduate, postgraduate and research degrees across 16 disciplines in Engineering, Sciences, Humanities and Management. About 596 faculty belonging to science and engineering departments and centres of the Institute are engaged in teaching, research and industrial consultancy.

IIT Madras

Improved acoustic modeling for automatic dysarthric speech recognition

2015 21st National Conference on Communications, NCC 2015

In this paper, we investigate various training methods for building deep neural network (DNN) based acoustic models for dysarthric speech data. Methods like multitask learning, knowledge distillation and model adaptation, which overcome data sparsity and model over-fitting problems are employed to study the merits of each method. In Knowledge distillation framework, some privilege information in addition to featurelabels pairs available only during training, is exploited to help the model learn better without using such previleged information during testing [1]; knowledge from one model can be distilled to another and thereby guiding it in learning better [2]. In this work, a DNN acoustic model trained using data pooled from Dysarthric speech data and parallel un-impaired data is used as the intelligent teacher while the student DNN model is trained using only Dysarthric speech. The target label for training the student model is a combination of hard aligned labels and those obtained from forward-pass through the teacher model. In addition to this technique, other knowledge sharing techniques like multitask learning were explored for Dysarthric speech data and have found to show a relative improvement of 11% over the corresponding baseline models. © 2017 IEEE.

2017 23rd National Conference on Communications, NCC 2017

DNN acoustic models for dysarthric speech

Interspeech 2016

Dysarthric Speech Recognition Using Kullback-Leibler Divergence-Based Hidden Markov Model

2014 IEEE Spoken Language Technology Workshop (SLT)

Automatic selection of speakers for improved acoustic modelling: recognition of disordered speech with sparse data

PLoS ONE

Severity-Based Adaptation with Limited Data for ASR to Aid Dysarthric Speakers

Language Resources and Evaluation

The TORGO database of acoustic and articulatory speech from speakers with dysarthria

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Generating exact lattices in the WFST framework

Journal	Data powered by Typeset2015 21st National Conference on Communications, NCC 2015
Publisher	Data powered by TypesetInstitute of Electrical and Electronics Engineers Inc.
Open Access	No