# ASR-Style Transcript Normalization Removes Useful Pragmatic Signal for Dialogue Act Classification

arXiv: https://arxiv.org/abs/2610.22934 · HTML: https://mlsanity.com/paper/2610.22934/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in ASR evaluation, bias and atypical speech, one of 11 directions in Speech and audio language models.
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 16 Oct 2026.

## Placed in

- Speech and audio language models / [ASR evaluation, bias and atypical speech](https://mlsanity.com/speech/asr-evaluation-bias-and-atypical-speech/)

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [ConvoKit: A Toolkit for the Analysis of Conversations](https://mlsanity.com/paper/2005.04246/) (2020)
- [CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions](https://mlsanity.com/paper/2408.16589/) (2024)
- [SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks](https://mlsanity.com/paper/2212.10525/) (2022)
- [Useful Blunders: Can Automated Speech Recognition Errors Improve Downstream Dementia Classification?](https://mlsanity.com/paper/2401.05551/) (2024)
- [An Approach to Improve Robustness of NLP Systems against ASR Errors](https://mlsanity.com/paper/2103.13610/) (2021)
- [Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors](https://mlsanity.com/paper/2310.16609/) (2023)
- [Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks](https://mlsanity.com/paper/2502.13645/) (2025)
- [What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition](https://mlsanity.com/paper/2107.02294/) (2021)
- [Emotion Detection in Speech Using Lightweight and Transformer-Based Models: A Comparative and Ablation Study](https://mlsanity.com/paper/2511.00402/) (2025)

## Abstract (arXiv)

Automatic speech recognition (ASR) pipelines often normalize transcripts by removing filled pauses and punctuation and expanding colloquial forms, potentially discarding cues useful for dialogue act classification. We evaluate nine transcript conditions across six classifiers (TF-IDF logistic regression, RoBERTa, BERT, ALBERT, GPT-2, and BiLSTM) and three conversational corpora (Switchboard, ICSI MRDA, and SLUE-HVB), supplemented by multi-seed experiments, normalization controls, and real-ASR evaluations. Across five random seeds, heavy normalization reduces Macro-F1 in all 15 neural model-corpus combinations under the original preprocessing protocols. Removal using the original filler and backchannel lexicon consistently degrades performance on MRDA and SLUE-HVB but produces mixed effects on Switchboard. Punctuation-aware TF-IDF experiments show that punctuation removal reduces Macro-F1 by 0.036 on Switchboard and 0.078 on MRDA, demonstrating that the original linear baseline's apparent insensitivity resulted from tokenization. Restricting filler removal to um, uh, and erm preserves degradation on MRDA but largely eliminates the SLUE-HVB effect, where the original lexicon removes class-defining backchannel expressions. These findings demonstrate that normalization effects depend on preprocessing definitions, feature extraction, and conversational context, supporting task-dependent rather than indiscriminate transcript normalization.