Add to ORKGStandard speaker adaptation algorithms perform poorly on dysarthric speech because of the limited phonemic repertoire of dysarthric speakers. In a previous paper, we proposed the use of "metamodels" to correct dysarthric speech. Here, we report on an improved technique that makes use of a cascade of Weighted Finite-State Transducers (WFSTs) at the confusion-matrix, word and language levels. This approach outperforms both standard MLLR and metamodels
Automatic speech recognition (ASR) is currently used in many assistive technologies, such as helping...
Dysarthria is a neurological speech disorder, which exhibits multi-fold disturbances in the speech p...
Automatic speech recognition (ASR) is currently used in many assistive technologies, such as helping...
Dysarthria is a motor speech disorder characterized by weakness, paralysis, or poor coordination of ...
Speech production errors characteristic of dysarthria are chiefly responsible for the low accuracy o...
Dysarthria is a motor speech disorder characterized by weakness, paralysis, or poor coordination of ...
Dysarthria is a motor speech disorder characterized by weakness, paralysis, or poor coordination of ...
In speech recognition systems language model (LMs) are often constructed by training and combining m...
We survey the use of weighted finite-state transducers (WFSTs) in speech recognition. We show that W...
In light of steady progress in machine learning, automatic speech recognition (ASR) is entering more...
This work addresses the mismatch problem between the distribution of training data (source) and test...
This work addresses the mismatch problem between the distribution of training data (source) and test...
This work addresses the mismatch problem between the distribution of training data (source) and test...
We survey the use of weighted finite-state transducers (WFSTs) in speech recognition. We show that W...
In speech recognition systems language model (LMs) are often constructed by training and combining m...
Automatic speech recognition (ASR) is currently used in many assistive technologies, such as helping...
Dysarthria is a neurological speech disorder, which exhibits multi-fold disturbances in the speech p...
Automatic speech recognition (ASR) is currently used in many assistive technologies, such as helping...
Dysarthria is a motor speech disorder characterized by weakness, paralysis, or poor coordination of ...
Speech production errors characteristic of dysarthria are chiefly responsible for the low accuracy o...
Dysarthria is a motor speech disorder characterized by weakness, paralysis, or poor coordination of ...
Dysarthria is a motor speech disorder characterized by weakness, paralysis, or poor coordination of ...
In speech recognition systems language model (LMs) are often constructed by training and combining m...
We survey the use of weighted finite-state transducers (WFSTs) in speech recognition. We show that W...
In light of steady progress in machine learning, automatic speech recognition (ASR) is entering more...
This work addresses the mismatch problem between the distribution of training data (source) and test...
This work addresses the mismatch problem between the distribution of training data (source) and test...
This work addresses the mismatch problem between the distribution of training data (source) and test...
We survey the use of weighted finite-state transducers (WFSTs) in speech recognition. We show that W...
In speech recognition systems language model (LMs) are often constructed by training and combining m...
Automatic speech recognition (ASR) is currently used in many assistive technologies, such as helping...
Dysarthria is a neurological speech disorder, which exhibits multi-fold disturbances in the speech p...
Automatic speech recognition (ASR) is currently used in many assistive technologies, such as helping...