Correcting Automated and Manual Speech Transcription Errors using Warped Language Models

by   Mahdi Namazifar, et al.

Masked language models have revolutionized natural language processing systems in the past few years. A recently introduced generalization of masked language models called warped language models are trained to be more robust to the types of errors that appear in automatic or manual transcriptions of spoken language by exposing the language model to the same types of errors during training. In this work we propose a novel approach that takes advantage of the robustness of warped language models to transcription noise for correcting transcriptions of spoken language. We show that our proposed approach is able to achieve up to 10 transcriptions of spoken language.


page 1

page 2

page 3

page 4


Language Models of Spoken Dutch

In Flanders, all TV shows are subtitled. However, the process of subtitl...

SCREEN: Learning a Flat Syntactic and Semantic Spoken Language Analysis Using Artificial Neural Networks

Previous approaches of analyzing spontaneously spoken language often hav...

Medication Error Detection Using Contextual Language Models

Medication errors most commonly occur at the ordering or prescribing sta...

Sharpness-Aware Minimization Improves Language Model Generalization

The allure of superhuman-level capabilities has led to considerable inte...

An Assessment of the Impact of OCR Noise on Language Models

Neural language models are the backbone of modern-day natural language p...

Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers

In theorem proving, the task of selecting useful premises from a large l...

Combining Learned Lyrical Structures and Vocabulary for Improved Lyric Generation

The use of language models for generating lyrics and poetry has received...