mlsanityData to 7 Oct 2026

Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correction

arXiv 2307.09744 ↗First posted 19 Jul 2023cs.CL cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

The integration of natural language processing (NLP) technologies into educational applications has shown promising results, particularly in the language learning domain. Recently, many spoken open-domain chatbots have been used as speaking partners, helping language learners improve their language skills. However, one of the significant challenges is the high word-error-rate (WER) when recognizing non-native/non-fluent speech, which interrupts conversation flow and leads to disappointment for learners. This paper explores the use of GPT4 for ASR error correction in conversational settings. In addition to WER, we propose to use semantic textual similarity (STS) and next response sensibility (NRS) metrics to evaluate the impact of error correction models on the quality of the conversation. We find that transcriptions corrected by GPT4 lead to higher conversation quality, despite an increase in WER. GPT4 also outperforms standard error correction methods without the need for in-domain training data.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 23 references that are in the map. First posted on arXiv 19 Jul 2023.

Builds on

20 of 23 references.

References · 20

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 230
  7. 2021Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Trainingcited by 148
  8. 2019A spelling correction model for end-to-end speech recognitioncited by 63
  9. 2019Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Modelcited by 52
  10. 2021Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checkingcited by 52
  11. 2020ASR Error Correction and Domain Adaptation Using Machine Translationcited by 48
  12. 2020Joint Contextual Modeling for ASR Correction and Language Understandingcited by 30
8 more
  1. 2021FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognitioncited by 27
  2. 2018Input Combination Strategies for Multi-Source Transformer Decodercited by 22
  3. 2021BART based semantic correction for Mandarin automatic speech recognition systemcited by 20
  4. 2020TLT-school: a Corpus of Non Native Children Speechcited by 10
  5. 2022SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognitioncited by 9
  6. 2022Cross-Modal ASR Post-Processing System for Error Correction and Utterance Rejectioncited by 6
  7. 2022Unsupervised domain adaptation for speech recognition with unsupervised error correctioncited by 5
  8. 2023Automatic Speech Recognition of Non-Native Child Speech for Language Learning Applicationscited by 3

Built on by

Cited by year

Citing papers per year: 2024: 2.

2 papers.

  1. 2024Recording for Eyes, Not Echoing to Ears: Contextualized Spoken-to-Written Conversion of ASR Transcriptscited by 2
  2. 2024Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Modelscited by 2