A comprehensive survey on automatic speech recognition using neural networks

Dhanjal, Amandeep Singh; Singh, Williamjeet

doi:10.1007/s11042-023-16438-y

Cited by 6 publications

(1 citation statement)

References 118 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pooling layers are used to reduce the dimension of feature maps. A fully connected layer at the end is used for classification (Papastratis, 2021;Dhanjal and Singh, 2023).…”

Section: Classifier Trainingmentioning

confidence: 99%

Self-supervised learning for Formosan speech representation and linguistic phylogeny

Hsieh,

Tseng,

Lian

et al. 2024

Front. Lang. Sci.

View full text Add to dashboard Cite

Formosan languages, spoken by the indigenous peoples of Taiwan, have unique roles in the reconstruction of Proto-Austronesian Languages. This paper presents a real-world Formosan language speech dataset, including 144 h of news footage for 16 Formosan languages, and uses self-supervised models to obtain and analyze their speech representations. Among the news footage, 13 h of the validated speech data of Formosan languages are selected, and a language classifier, based on XLSR-53, is trained to classify the 16 Formosan languages with an accuracy of 86%. We extracted and analyzed the speech vector representations learned from the model and compared them with 152 manually coded linguistic typological features. The comparison shows that the speech vectors reflect Formosan languages' phonological and morphological aspects. Furthermore, the speech vectors and linguistic features are used to construct a linguistic phylogeny, and the resulting genealogical grouping corresponds with previous literature. These results suggest that we can investigate the current real-world language usages through the speech model, and the dataset opens a window to look into the Formosan languages in vivo.

show abstract

“…Pooling layers are used to reduce the dimension of feature maps. A fully connected layer at the end is used for classification (Papastratis, 2021;Dhanjal and Singh, 2023).…”

Section: Classifier Trainingmentioning

confidence: 99%