Investigating ASR Error Correction with Large Language Model and ...

Automatically Detecting Likely Edits in Clinical Notes Created Using ...

This paper investigates novel methods for automatic detection of edit regions within the transcripts, including both putative ASR errors but also regions that ...

Crossmodal ASR error correction with discrete speech units

In this work, we tackle an understudied issue: the Low-Resource Out-of-Domain (LROOD) problem, by investigating crossmodal AEC on very limited downstream data.

Evaluation of the effectiveness and efficiency of state-of-the-art ...

This has led to a proliferation of studies that investigate Error detection and classification in Automatic Speech Recognition (ASR) systems.

HyPoradise: An Open Baseline for Generative Speech Recognition ...

We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction.

Mondegreen: A Post-Processing Solution to Speech Recognition ...

Statistical error correction methods for domain-specific ASR systems. In International Conference on Statistical Language and Speech Processing.

Contextualized Speech Recognition: Rethinking Second-Pass ...

Contextualized ASR tasks require ... Given n-best hypotheses, we leverage prompting with a large language model for contextualized second-pass generation.

Can large language models identify and correct their mistakes?

In “LLMs cannot find reasoning errors, but can correct them!”, we test state-of-the-art LLMs on mistake finding and output correction separately ...

CAN GENERATIVE LARGE LANGUAGE MODELS PERFORM ASR ...

Among these, ASR error correction which automatically identifies errors within the. ASR hypothesis and outputs the corrected transcription is widely used. • ...

Artificial intelligence - Reasoning, Algorithms, Automation - Britannica

In large language model (LLM), the word large refers to the parameters, or ... (ASR) system. After breaking down the speech, the VA analyzes and ...