Self-supervised speech representations still struggle with african american vernacular english

K Chang, YH Chou, J Shi, HM Chen, N Holliday… - arXiv preprint arXiv …, 2024 - arxiv.org
Underperformance of ASR systems for speakers of African American Vernacular English
(AAVE) and other marginalized language varieties is a well-documented phenomenon, and …

EFL lecturers' practice, perception, and evaluation of English as the medium of instruction in tertiary education

E Saragih - Issues in language studies, 2024 - publisher.unimas.my
Higher education institutions in non-English speaking countries, such as Indonesia, have
practised English as a Medium of Instruction (EMI) in teaching-learning activities. Previous …

Edge computing solutions supporting voice recognition services for speakers with dysarthria

D Mulfari, L Carnevale, A Galletta… - 2023 IEEE/ACM 23rd …, 2023 - ieeexplore.ieee.org
In the framework of Automatic Speech Recognition (ASR), the synergism between edge
computing and artificial intelligence has led to the development of intelligent objects that …

CAST: Context-association architecture with simulated long-utterance training for mandarin speech recognition

Y Ming, B Lyu, Z Li - Speech Communication, 2023 - Elsevier
Abstract End-to-end (E2E) models are widely used because they significantly improve the
performance of automatic speech recognition (ASR). However, based on the limitations of …

Reducing geographic disparities in automatic speech recognition via elastic weight consolidation

VA Trinh, P Ghahremani, B King, J Droppo… - arXiv preprint arXiv …, 2022 - arxiv.org
We present an approach to reduce the performance disparity between geographic regions
without degrading performance on the overall user population for ASR. A popular approach …

Comparison of noise reduction techniques for dysarthric speech recognition

D Mulfari, G Campobello, G Gugliandolo… - 2022 IEEE …, 2022 - ieeexplore.ieee.org
The paper investigates the impact of denoising techniques on a deep learning recognition
system for speak-ers with dysarthria, ie, a neuromotor speech disorder which compromises …

Examining the effect of phonological awareness instruction on EFL learners' pronunciation and motivation

IK Wardana, PT Astuti… - Erudita: Journal of …, 2022 - e-journal.uingusdur.ac.id
ELT teachers in Indonesia mostly apply an integrative language teaching approach to cover
the linguistic elements of language skills. However, the pronunciation in speaking exposure …

Domain generalization for language-independent automatic speech recognition

H Gao, J Ni, Y Zhang, K Qian, S Chang… - Frontiers in Artificial …, 2022 - frontiersin.org
A language-independent automatic speech recognizer (ASR) is one that can be used for
phonetic transcription in languages other than the languages in which it was trained …

INTapt: Information-Theoretic Adversarial Prompt Tuning for Enhanced Non-Native Speech Recognition

E Yoon, HS Yoon, J Harvill… - arXiv preprint arXiv …, 2023 - arxiv.org
Automatic Speech Recognition (ASR) systems have attained unprecedented performance
with large speech models pre-trained based on self-supervised speech representation …

Strengthening the Expertise of Special Assistant Teachers in the Implementation of Inclusive Education Management at the Early Childhood Education Level Based …

BS Hanur, R Sari - Jurnal Pengabdian dan Pemberdayaan …, 2021 - jppmi.ptti.web.id
In accordance with the mandate of Law Number 20 of 2003 concerning the National
Education System, Article 4 paragraph (1) education in Indonesia is carried out in a …