Voice activity detection for children's read speech recognition in noisy conditions

Pasad, Ankita; Sabu, Kamini; Rao, Preeti

doi:10.1109/ncc.2017.8077072

Cited by 4 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The underlying speech attributes that we take into account, based on our observations and intuition, are the following: 1. Pauses: Silences are obtained from a voice-activitydetection (VAD) module [20] that uses energy and harmonicity with temporal smoothness constraints to detect non-speech frames at 10 ms intervals. To exclude plosives, silences exceeding 200 ms are defined as pauses.…”

Section: Acoustic Features For Classificationmentioning

confidence: 99%

Predicting lexical skills from oral reading with acoustic measures

Vitthal¹,

Shreeharsha²,

Sabu³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Literacy assessment is an important activity for education administrators across the globe. Typically achieved in a school setting by testing a child's oral reading, it is intensive in human resources. While automatic speech recognition (ASR) is a potential solution to the problem, it tends to be computationally expensive for hand-held devices apart from needing languageand accent-specific speech for training. In this work, we propose a system to predict the word-decoding skills of a student based on simple acoustic features derived from the recording. We first identify a meaningful categorization of word-decoding skills by analyzing a manually transcribed data set of children's oral reading recordings. Next the automatic prediction of the category is attempted with the proposed acoustic features. Pause statistics, syllable rate and spectral and intensity dynamics are found to be reliable indicators of specific types of oral reading deficits, providing useful feedback by discriminating the different characteristics of beginning readers. This computationally simple and language-agnostic approach is found to provide a performance close to that obtained using a language dependent ASR that required considerable tuning of its parameters.

show abstract

Section: Acoustic Features For Classificationmentioning

confidence: 99%