most citedInclusive ASR for Disfluent Speech: Cascaded Large-Scale Self-Supervised Learning with Targeted Fine-Tuning and Data Augmentation

14 citations · 14 across the 2 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2024

Lost in Transcription: Identifying and Quantifying the Accuracy Biases of Automatic Speech Recognition Systems Against Disfluent Speech

Dena Mujtaba, Nihar R. Mahapatra, Megan Arney +4

Automatic speech recognition (ASR) systems, increasingly prevalent in education, healthcare, employment, and mobile technology, face significant challenges in inclusivity, particul…