FlanEC: Exploring Flan-T5 for Post-ASR Error Correction

Moreno La Quatra, Valerio Mario Salerno, Yu Tsao, Sabato Marco Siniscalchi
1/22/2025
cs.CLcs.AIcs.SD

No official code found. Best implementation: MorenoLaQuatra/FlanEC (12 stars, MIT, last commit 2025-01-23).

Abstract

In this paper, we present an encoder-decoder model leveraging Flan-T5 for post-Automatic Speech Recognition (ASR) Generative Speech Error Correction (GenSEC), and we refer to it as FlanEC. We explore its application within the GenSEC framework to enhance ASR outputs by mapping n-best hypotheses into a single output sentence. By utilizing n-best lists from ASR models, we aim to improve the linguistic correctness, accuracy, and grammaticality of final ASR transcriptions. Specifically, we investigate whether scaling the training data and incorporating diverse datasets can lead to significant improvements in post-ASR error correction. We evaluate FlanEC using the HyPoradise dataset, providing a comprehensive analysis of the model's effectiveness in this domain. Furthermore, we assess the proposed approach under different settings to evaluate model scalability and efficiency, offering valuable insights into the potential of instruction-tuned encoder-decoder models for this task.

View on arXivView PDF

Code Implementations(1)

MorenoLaQuatra/FlanECCommunity100%
MIT

This repository contains the code and experiments for the paper "Exploring Flan-T5 for Post-ASR Error Correction".

121PythonJun 25, 20241 years agoMIT

Similar Papers

ASR Error Correction using Large Language Models

86% match2024

Evolutionary Prompt Design for LLM-Based Post-ASR Error Correction

85% match1 repo182024

Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition

84% match2024

HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models

84% match1 repo942026

Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models

84% match2024

Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM

83% match2025

Cite this paper

@article{quatra2025flanec,
  title  = {FlanEC: Exploring Flan-T5 for Post-ASR Error Correction},
  author = {Moreno La Quatra and Valerio Mario Salerno and Yu Tsao and Sabato Marco Siniscalchi},
  year   = {2025},
  eprint = {2501.12979},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.12979v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.12979.svg)](https://codeofpaper.com/paper/2501.12979)

Discussion