# HypR: A comprehensive study for ASR hypothesis revising with a reference corpus

arXiv: https://arxiv.org/abs/2309.09838 · HTML: https://mlsanity.com/paper/2309.09838/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 18 Sep 2023.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [A spelling correction model for end-to-end speech recognition](https://mlsanity.com/paper/1902.07178/) (2019)
- [Can Generative Large Language Models Perform ASR Error Correction?](https://mlsanity.com/paper/2307.04172/) (2023)
- [FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition](https://mlsanity.com/paper/2105.03842/) (2021)
- [RescoreBERT: Discriminative Speech Recognition Rescoring with BERT](https://mlsanity.com/paper/2202.01094/) (2022)
- [FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition](https://mlsanity.com/paper/2109.14420/) (2021)
- [Innovative Bert-based Reranking Language Models for Speech Recognition](https://mlsanity.com/paper/2104.04950/) (2021)
- [BART based semantic correction for Mandarin automatic speech recognition system](https://mlsanity.com/paper/2104.05507/) (2021)
- [Error Correction in ASR using Sequence-to-Sequence Models](https://mlsanity.com/paper/2202.01157/) (2022)
- [Non-autoregressive Transformer-based End-to-end ASR using BERT](https://mlsanity.com/paper/2104.04805/) (2021)
- [A context-aware knowledge transferring strategy for CTC-based ASR](https://mlsanity.com/paper/2210.06244/) (2022)
- [An Empirical Study of Efficient ASR Rescoring with Transformers](https://mlsanity.com/paper/1910.11450/) (2019)
- [SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition](https://mlsanity.com/paper/2212.01039/) (2022)
- [Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling](https://mlsanity.com/paper/2205.12986/) (2022)
- [Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning](https://mlsanity.com/paper/2004.08097/) (2020)
- [Masked Audio Text Encoders are Effective Multi-Modal Rescorers](https://mlsanity.com/paper/2305.07677/) (2023)

## Built on by (most cited first, 1 of 1)

- [Robust ASR Error Correction with Conservative Data Filtering](https://mlsanity.com/paper/2407.13300/) (2024)

## Abstract (arXiv)

With the development of deep learning, automatic speech recognition (ASR) has made significant progress. To further enhance the performance of ASR, revising recognition results is one of the lightweight but efficient manners. Various methods can be roughly classified into N-best reranking modeling and error correction modeling. The former aims to select the hypothesis with the lowest error rate from a set of candidates generated by ASR for a given input speech. The latter focuses on detecting recognition errors in a given hypothesis and correcting these errors to obtain an enhanced result. However, we observe that these studies are hardly comparable to each other, as they are usually evaluated on different corpora, paired with different ASR models, and even use different datasets to train the models. Accordingly, we first concentrate on providing an ASR hypothesis revising (HypR) dataset in this study. HypR contains several commonly used corpora (AISHELL-1, TED-LIUM 2, and LibriSpeech) and provides 50 recognition hypotheses for each speech utterance. The checkpoint models of ASR are also published. In addition, we implement and compare several classic and representative methods, showing the recent research progress in revising speech recognition results. We hope that the publicly available HypR dataset can become a reference benchmark for subsequent research and promote this field of research to an advanced level.