The limitations of data perturbation for ASR of learner data in under-resourced languages

Créateur:

Jaco Badenhorst

Febe de Wet

Éditeur:

IEEE

Hôte:

Visit

Tasks

automatic speech recognition speech processing

Similaires

Gauging the accuracy of automatic speech data harvesting in five under-resourced languagesMultilingual training set selection for ASR in under-resourced Malian languagesSpeech recognition for under-resourced languages: Data sharing in hidden Markov model systemsData-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced LanguagesImproving Speech Recognition for Under-resourced Languages Utilizing Audio-codecs for Data AugmentationMultilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages

Gauging the accuracy of automatic speech data harvesting in five under-resourced languages

Recent research on deep-learning architectures has resulted in substantial improvements in automatic

Multilingual training set selection for ASR in under-resourced Malian languages

We present first speech recognition systems for the two severely under-resourced Malian languages Ba

Speech recognition for under-resourced languages: Data sharing in hidden Markov model systems

For purposes of automated speech recognition in under-resourced environments, t

Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages

Hate speech is a global phenomenon, but most hate speech datasets so far focus on English-language c

Improving Speech Recognition for Under-resourced Languages Utilizing Audio-codecs for Data Augmentation

Presenter: Nirayo Hailu Gebreegziabher, Ingo Siegert, Andreas Nürnberger, MMSP 2020, Virtual Event,

Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages

In this work, we explore the benefits of using multilingual bottleneck features (mBNF) in acoustic m