# Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding

arXiv: https://arxiv.org/abs/2410.15609 · HTML: https://mlsanity.com/paper/2410.15609/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators](https://mlsanity.com/paper/2111.13057/) (2021)
- [How Robust Are Character-Based Word Embeddings in Tagging and MT Against Wrod Scramlbing or Randdm Nouse?](https://mlsanity.com/paper/1704.04441/) (2017)
- [Learning ASR-Robust Contextualized Embeddings for Spoken Language Understanding](https://mlsanity.com/paper/1909.10861/) (2019)
- [Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study](https://mlsanity.com/paper/2008.07683/) (2020)
- [Error Correction in ASR using Sequence-to-Sequence Models](https://mlsanity.com/paper/2202.01157/) (2022)
- [Data Augmentation for Training Dialog Models Robust to Speech Recognition Errors](https://mlsanity.com/paper/2006.05635/) (2020)
- [Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation](https://mlsanity.com/paper/1910.03009/) (2019)
- [Hallucination of speech recognition errors with sequence to sequence learning](https://mlsanity.com/paper/2103.12258/) (2021)
- [Robust Neural Machine Translation for Clean and Noisy Speech Transcripts](https://mlsanity.com/paper/1910.10238/) (2019)
- [TOD-DA: Towards Boosting the Robustness of Task-oriented Dialogue Modeling on Spoken Conversations](https://mlsanity.com/paper/2112.12441/) (2021)
- [An Approach to Improve Robustness of NLP Systems against ASR Errors](https://mlsanity.com/paper/2103.13610/) (2021)
- [ASR Error Correction with Constrained Decoding on Operation Prediction](https://mlsanity.com/paper/2208.04641/) (2022)
- [Mitigating the Impact of Speech Recognition Errors on Chatbot using Sequence-to-Sequence Model](https://mlsanity.com/paper/1709.07862/) (2017)
- [Abstractive Headline Generation for Spoken Content by Attentive Recurrent Neural Networks with ASR Error Modeling](https://mlsanity.com/paper/1612.08375/) (2016)
- [Discovering Lexical Similarity Through Articulatory Feature-based Phonetic Edit Distance](https://mlsanity.com/paper/2008.06865/) (2020)
- [Robust Unstructured Knowledge Access in Conversational Dialogue with ASR Errors](https://mlsanity.com/paper/2211.03990/) (2022)

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

- [Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks](https://mlsanity.com/paper/2502.13645/) (2025)

## Abstract (arXiv)

Recently, pre-trained language models (PLMs) have been increasingly adopted in spoken language understanding (SLU). However, automatic speech recognition (ASR) systems frequently produce inaccurate transcriptions, leading to noisy inputs for SLU models, which can significantly degrade their performance. To address this, our objective is to train SLU models to withstand ASR errors by exposing them to noises commonly observed in ASR systems, referred to as ASR-plausible noises. Speech noise injection (SNI) methods have pursued this objective by introducing ASR-plausible noises, but we argue that these methods are inherently biased towards specific ASR systems, or ASR-specific noises. In this work, we propose a novel and less biased augmentation method of introducing the noises that are plausible to any ASR system, by cutting off the non-causal effect of noises. Experimental results and analyses demonstrate the effectiveness of our proposed methods in enhancing the robustness and generalizability of SLU models against unseen ASR systems by introducing more diverse and plausible ASR noises in advance.