this study intended to develop a model describing speaking strategies for efl learners by taking into account the effects of learners’ gender and proficiency on the application of strategies. accordingly, this study was planned to have two main analyses, namely qualitative and quantitative. in this respect, 30 efl learners' viewpoints were sought, and then, based on the elicited responses, a 21...

The goal of this study is to evaluate to what extent listeners are capable of distinguishing between professional speaking styles based only on prosodic cues. The four speaking styles contemplated in the study – TV news, religious, political, and interview speech – were recorded in the context of normal use from Brazilian television and low-pass filtered to remove semantic information. The part...

This study presents an approach to the task of automatically classifying and detecting speaking styles. The detection of speaking styles is useful for the segmentation of multimedia data into consistent parts and has important applications, such as identifying speech segments to train acoustic models for speech recognition. In this work the database consists of daily news broadcasts in Portugue...

Accuracy of content have not been fully utilized in the previous studies on automated speaking assessment. Compared to writing tests, responses in speaking tests are noisy (due to recognition errors), full of incomplete sentences, and short. To handle these challenges for doing content-scoring in speaking tests, we propose two new methods based on information extraction (IE) and machine learnin...

Recently, in the language testing field, automatic speech recognition (ASR) technology has been used to automatically score speaking tests. This paper investigates the impact of audio quality on ASR-based automatic speaking assessment. Using the read speech data in the International English Speaking Test (IEST) practice test, we annotated audio quality and compared scores rated by humans, speec...

A real-world speech recognition system encounters several speaking styles and speaking rates and its accuracy depends highly on the speaking rate, i.e., degrades sharply with very fast or very slow speech (including hyperarticulated speech) In this paper, we propose a generic modeling scheme to capture a range of speaking rates from very slow to very fast with the use of decision trees. This ap...