mlsanityData to 7 Oct 2026

Adapting an Unadaptable ASR System

arXiv 2306.01208 ↗First posted 1 Jun 2023eess.AS cs.CL cs.SDcited by 3

Not on the map. Why?

Abstract (arXiv)

As speech recognition model sizes and training data requirements grow, it is increasingly common for systems to only be available via APIs from online service providers rather than having direct access to models themselves. In this scenario it is challenging to adapt systems to a specific target domain. To address this problem we consider the recently released OpenAI Whisper ASR as an example of a large-scale ASR system to assess adaptation methods. An error correction based approach is adopted, as this does not require access to the model, but can be trained from either 1-best or N-best outputs that are normally available via the ASR API. LibriSpeech is used as the primary target domain for adaptation. The generalization ability of the system in two distinct dimensions are then evaluated. First, whether the form of correction model is portable to other speech recognition domains, and secondly whether it can be used for ASR models having a different architecture.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 20 of its 33 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

20 of 33 references.

References · 20

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  5. 2015Listen, Attend and Spellcited by 542
  6. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languagescited by 228
  7. 2018TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationcited by 224
  8. 2020Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognitioncited by 80
  9. 2020A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognitioncited by 73
  10. 2019A spelling correction model for end-to-end speech recognitioncited by 63
  11. 2019Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Modelcited by 52
  12. 2023N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Spacecited by 41
8 more
  1. 2021Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Modelscited by 25
  2. 2021BART based semantic correction for Mandarin automatic speech recognition systemcited by 20
  3. 2021Neural Inverse Text Normalizationcited by 19
  4. 2022Error Correction in ASR using Sequence-to-Sequence Modelscited by 19
  5. 2022Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correctioncited by 10
  6. 2022Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASRcited by 9
  7. 2020Black-box Adaptation of ASR for Accented Speechcited by 8
  8. 2022RED-ACE: Robust Error Detection for ASR using Confidence Embeddingscited by 8

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2023Can Generative Large Language Models Perform ASR Error Correction?cited by 56
  2. 2024ASR Error Correction using Large Language Modelscited by 23
  3. 2023Wiki-En-ASR-Adapt: Large-scale synthetic dataset for English ASR Customizationcited by 0