Specific acoustic models for spontaneous and dictated style in indonesian speech recognition

Vista, Candra Bella; Satriawan, Cil Hardianto; Lestari, Dessi Puji; Widyantoro, Dwi H.

doi:10.1088/1742-6596/978/1/012059

Cited by 3 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It offers the flexibility of a word processing editor where an individual can edit the text to perfection. Some work has been done to differentiate spontaneously and dictated speech in an Indonesian dataset [137]. It would be interesting to see if writing style differences exist between dictated text and OSN text.…”

Section: Concluding Remarks and Future Workmentioning

confidence: 99%

Online Social Networks and Writing Styles–A Review of the Multidisciplinary Literature

2020

View full text Add to dashboard Cite

In recent years, author identification has become an active research area, where the major differences are caused by paper or online medium, mode of entry and target audience. Much research has been devoted to analyzing writing styles in handwritten, word-processed and online social networks (OSN) texts. Word processing editors that typically include spell and grammar checkers may influence the writing style as it allows an individual to edit a piece of text to perfection. Thus, similarities may exist between OSN and word-processed texts. Moreover, none of the studies to date have made a detailed comparison of the writing styles across multidisciplinary factors. This paper attempts to close the gap between the writing styles in pre-and post-Internet periods as well as provide an in-depth comparison of the writing styles in OSN texts across three major factors: demographics, personality & behavior, and cybersecurity. The aim is to learn from past literature as we advance these techniques to OSN texts. Thus, in this paper, we also propose a novel machine learning prediction model based on tense morphology, to classify age and gender from English blogs, and the PAN 2013 dataset. This model achieves an accuracy of 94%-98% and 95%-97% for age and gender, respectively. INDEX TERMS Online social networks, survey, writing styles.

show abstract

Section: Concluding Remarks and Future Workmentioning

confidence: 99%