Afrispeech-200: Pan-african accented speech dataset for clinical and general domain asr

T Olatunji, T Afonja, A Yadavalli, CC Emezue… - Transactions of the …, 2023‏ - direct.mit.edu
Africa has a very poor doctor-to-patient ratio. At very busy clinics, doctors could see 30+
patients per day—a heavy patient burden compared with developed countries—but …

Capitalization and punctuation restoration: a survey

V Păiş, D Tufiş - Artificial Intelligence Review, 2022‏ - Springer
Ensuring proper punctuation and letter casing is a key pre-processing step towards applying
complex natural language processing algorithms. This is especially significant for textual …

Revolutionizing radiological analysis: The future of French language automatic speech recognition in healthcare

M Jelassi, O Jemai, J Demongeot - Diagnostics, 2024‏ - mdpi.com
This study introduces a specialized Automatic Speech Recognition (ASR) system,
leveraging the Whisper Large-v2 model, specifically adapted for radiological applications in …

Listen, know and spell: Knowledge-infused subword modeling for improving asr performance of oov named entities

N Das, M Sunkara, D Bekal, DH Chau… - ICASSP 2022-2022 …, 2022‏ - ieeexplore.ieee.org
Automatic speech recognition (ASR) is increasingly being used in specialized domains such
as medical ASR and news transcription. Owing to the lack of high quality annotated speech …

Multimodal semi-supervised learning framework for punctuation prediction in conversational speech

M Sunkara, S Ronanki, D Bekal, S Bodapati… - arxiv preprint arxiv …, 2020‏ - arxiv.org
In this work, we explore a multimodal semi-supervised learning approach for punctuation
prediction by learning representations from large amounts of unlabelled audio and text data …

Fullstop: Punctuation and segmentation prediction for dutch with transformers

V Vandeghinste, O Guhr - Language Resources and Evaluation, 2024‏ - Springer
When applying automated speech recognition (ASR) for Belgian Dutch, the output consists
of an unsegmented stream of words, without any punctuation. A next step is to perform …

Automatic speech recognition performance for digital scribes: a performance comparison between general-purpose and specialized models tuned for patient-clinician …

BD Tran, R Mangu, M Tai-Seale… - AMIA Annual …, 2023‏ - pmc.ncbi.nlm.nih.gov
One promising solution to address physician data entry needs is through the development of
so-called “digital scribes,” or tools which aim to automate clinical documentation via …

Multi-output RNN-T joint networks for multi-task learning of ASR and auxiliary tasks

W Wang, D Zhao, S Ding, H Zhang… - ICASSP 2023-2023 …, 2023‏ - ieeexplore.ieee.org
We propose a multi-output joint network architecture for RNN-T transducer, for multi-task
modeling of ASR and auxiliary tasks that rely on ASR outputs. Each output of the joint …

Remember the context! asr slot error correction through memorization

D Bekal, A Shenoy, M Sunkara… - 2021 IEEE Automatic …, 2021‏ - ieeexplore.ieee.org
Accurate recognition of slot values such as domain specific words or named entities by
automatic speech recognition (ASR) systems forms the core of the Goal-oriented Dialogue …

Making punctuation restoration robust and fast with multi-task learning and knowledge distillation

M Hentschel, E Tsunoo, T Okuda - ICASSP 2021-2021 IEEE …, 2021‏ - ieeexplore.ieee.org
In punctuation restoration, we try to recover the missing punctuation from automatic speech
recognition output to improve understandability. Currently, large pre-trained transformers …