State-of-the-art Automatic Speech Recognition (ASR) models struggle to handle accented speech, particularly if the target accent is under-represented in the training data. The acoustic variations presented by an unfamiliar accent, render the ASR polyphone decision tree (PDT) and its associated Gaussian mixture models (GMM) misfit to the test data. In this paper, we improve on the previous work of adapting the polyphone decision tree, using a semi-continuous model based approach to address the problem of data sparsity. We extend the existing PDT to introduce additional states with shared parameters, corresponding to the new contextual variations identified in the adaptation data, while still robustly estimating the state based parameters on ...
Automatic speech recognition technology has developed rapidly in the past decade. Applications of th...
In this paper, we analyze the impact of five Arabic dialects on the front-end and pronunciation dict...
This paper investigates techniques to compensate for the effects of regional accents of British Engl...
<p>Accented speech that is under-represented in the training data still suffers high Word Error Rate...
The general goal of this thesis is to improve the performance of state-of-the-art statistical automa...
Accented speech that is under-represented in the training data still suffers high Word Error Rate (W...
This paper is concerned with automatic speech recognition (ASR) for accented speech. Given a small a...
Accent variability is an important factor in speech that can sig-nificantly degrade automatic speech...
With the distribution of speech technology products all over the world, the fast and efficient porta...
Accent is cited as an issue for speech recognition systems. Our experiments showed that the ASR word...
Summarization: Several adaptation approaches have been proposed in an effort to improve the speech r...
Several adaptation approaches have been proposed in an eort to improve the speech recognition perfor...
<p>We experiment with active learning for speech recognition in the context of accent adaptation. We...
We experiment with active learning for speech recognition in the context of accent adaptation. We ad...
Accented speech that is under-represented in the training data still suffers high Word Error Rate (W...
Automatic speech recognition technology has developed rapidly in the past decade. Applications of th...
In this paper, we analyze the impact of five Arabic dialects on the front-end and pronunciation dict...
This paper investigates techniques to compensate for the effects of regional accents of British Engl...
<p>Accented speech that is under-represented in the training data still suffers high Word Error Rate...
The general goal of this thesis is to improve the performance of state-of-the-art statistical automa...
Accented speech that is under-represented in the training data still suffers high Word Error Rate (W...
This paper is concerned with automatic speech recognition (ASR) for accented speech. Given a small a...
Accent variability is an important factor in speech that can sig-nificantly degrade automatic speech...
With the distribution of speech technology products all over the world, the fast and efficient porta...
Accent is cited as an issue for speech recognition systems. Our experiments showed that the ASR word...
Summarization: Several adaptation approaches have been proposed in an effort to improve the speech r...
Several adaptation approaches have been proposed in an eort to improve the speech recognition perfor...
<p>We experiment with active learning for speech recognition in the context of accent adaptation. We...
We experiment with active learning for speech recognition in the context of accent adaptation. We ad...
Accented speech that is under-represented in the training data still suffers high Word Error Rate (W...
Automatic speech recognition technology has developed rapidly in the past decade. Applications of th...
In this paper, we analyze the impact of five Arabic dialects on the front-end and pronunciation dict...
This paper investigates techniques to compensate for the effects of regional accents of British Engl...