FlanEC: Exploring Flan-T5 for Post-ASR Error Correction
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 22 Jan 2025.
Builds on
27 of 40 references.
References · 27
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
- 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
- 2022Emergent Abilities of Large Language Modelscited by 2,483
- 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
- 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
- 2022A Survey on In-context Learningcited by 717
- 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
15 more
- 2016Lip Reading Sentences in the Wildcited by 226
- 2018TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationcited by 224
- 2023Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluationcited by 134
- 2017An analysis of incorporating an external language model into a sequence-to-sequence modelcited by 109
- 2023Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Promptingcited by 71
- 2023CoEdIT: Text Editing by Task-Specific Instruction Tuningcited by 67
- 2018A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognitioncited by 66
- 2023INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Modelscited by 62
- 2023N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Spacecited by 41
- 2023HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Modelscited by 41
- 2023Can Whisper perform speech-based in-context learning?cited by 35
- 2024Large Language Models are Efficient Learners of Noise-Robust Speech Recognitioncited by 30
- 2024Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networkscited by 8
- 2021Mondegreen: A Post-Processing Solution to Speech Recognition Error Correction for Voice Search Queriescited by 4
- 2024Quantifying the Role of Textual Predictability in Automatic Speech Recognitioncited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.