Correcting Automated and Manual Speech Transcription Errors using Warped Language Models
This work addresses transcription accuracy for speech processing applications, but it is incremental as it builds on existing warped language models.
The paper tackled the problem of correcting errors in automated and manual speech transcriptions by leveraging warped language models trained to be robust to transcription noise, achieving up to a 10% reduction in word error rates.
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% reduction in word error rates of both automatic and manual transcriptions of spoken language.