Efficient automatic punctuation restoration using bidirectional transformers with robust inference

M Courtland, A Faulkner… - Proceedings of the 17th …, 2020 - aclanthology.org
Though people rarely speak in complete sentences, punctuation confers many benefits to
the readers of transcribed speech. Unfortunately, most ASR systems do not produce …

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 …

Joint word-and character-level embedding CNN-RNN models for punctuation restoration

MÁ Tündik, G Szaszák - 2018 9th IEEE International …, 2018 - ieeexplore.ieee.org
The sequence-to-sequence modelling paradigm has been successfully used in automatic
punctuation of text generated by Automatic Speech Recognizers (ASR), using bidirectional …

A survey on bias in machine learning research

A Mikołajczyk-Bareła, M Grochowski - arXiv preprint arXiv:2308.11254, 2023 - arxiv.org
Current research on bias in machine learning often focuses on fairness, while overlooking
the roots or causes of bias. However, bias was originally defined as a" systematic error," …

Efficient Text Analysis with Pre-Trained Neural Network Models

J Cui, H Lu, W Wang, S Kang, L He… - 2022 IEEE Spoken …, 2023 - ieeexplore.ieee.org
This paper investigates the application of pre-trained BERT model in three classic text
analysis tasks: Chinese grapheme-to-phoneme (G2P), text normalization (TN) and sentence …

[PDF][PDF] An audio-based sequential punctuation model for asr and its effect on human readability

G Szaszák - Acta Polytechnica Hungarica, 2019 - epa.niif.hu
Inserting punctuation marks into the word chain hypothesis produced by automatic speech
recognition (ASR) has long been a neglected task. In several application domains of ASR …

[图书][B] Leveraging Prosody for Punctuation Prediction of Spontaneous Speech

JY Cho - 2022 - search.proquest.com
Clarity and precision of written text benefits from correct punctuation. For scripts that lack
punctuation, such as conversational speech, there can be errors in accurately interpreting …

Case study of an on-premise data warehouse configuration

B Bogdándy, Á Kovács, Z Tóth - 2020 11th IEEE International …, 2020 - ieeexplore.ieee.org
The development of machine learning over the years has facilitated the joint upsurge of
complex cognitive infocommunication systems. Machine Learning methods are vital …

Improving the Readability of Unformatted Text using Multitask Attention Networks

AP Viet, MT Nguyen, LB Thu… - 2021 13th International …, 2021 - ieeexplore.ieee.org
Unformatted text is a big obstacle to human reading and degrades the performance of many
downstream language understanding tasks. To improve the readability, this paper proposes …

[HTML][HTML] Características prosódicas associadas aos sinais de pontuação: uma revisão de escopo

JC Galdino, KFT da SILVA… - Cadernos de …, 2021 - cadernos.abralin.org
The purpose of this article is to present the scope review of the prosodic features associated
with punctuation marks. A bibliographic survey was carried out based on the search for …