# Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features

arXiv: https://arxiv.org/abs/2309.07733 · HTML: https://mlsanity.com/paper/2309.07733/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 56 references that are in the map.
- First posted on arXiv 14 Sep 2023.

## Builds on (most cited first, 30 of 33)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Speech Model Pre-training for End-to-End Spoken Language Understanding](https://mlsanity.com/paper/1904.03670/) (2019)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [OpenXAI: Towards a Transparent Evaluation of Model Explanations](https://mlsanity.com/paper/2206.11104/) (2022)
- [TorchAudio: Building Blocks for Audio and Speech Processing](https://mlsanity.com/paper/2110.15018/) (2021)
- [Contrastive Explanations for Model Interpretability](https://mlsanity.com/paper/2103.01378/) (2021)
- ["What is Relevant in a Text Document?": An Interpretable Machine Learning Approach](https://mlsanity.com/paper/1612.07843/) (2016)
- [Discretized Integrated Gradients for Explaining Language Models](https://mlsanity.com/paper/2108.13654/) (2021)
- [Toward Interpretable Music Tagging with Self-Attention](https://mlsanity.com/paper/1906.04972/) (2019)
- [Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities](https://mlsanity.com/paper/2207.11345/) (2022)
- [Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations](https://mlsanity.com/paper/2112.09669/) (2021)
- [Human Interpretation of Saliency-based Explanation Over Text](https://mlsanity.com/paper/2201.11569/) (2022)
- [Improving Fairness and Robustness in End-to-End Speech Recognition through unsupervised clustering](https://mlsanity.com/paper/2306.06083/) (2023)
- [Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition](https://mlsanity.com/paper/2305.18011/) (2023)
- [ITALIC: An Italian Intent Classification Dataset](https://mlsanity.com/paper/2306.08502/) (2023)

## Built on by (most cited first, 7 of 7)

- [Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps](https://mlsanity.com/paper/2402.17954/) (2024)
- [SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation](https://mlsanity.com/paper/2411.01710/) (2024)
- [Identifying and typifying demographic unfairness in phoneme-level embeddings of self-supervised speech recognition models](https://mlsanity.com/paper/2604.22631/) (2026)
- [On the reliability of feature attribution methods for speech classification](https://mlsanity.com/paper/2505.16406/) (2025)
- [Cross-Attention is Half Explanation in Speech-to-Text Models](https://mlsanity.com/paper/2509.18010/) (2025)
- ["KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding](https://mlsanity.com/paper/2505.20176/) (2025)
- [A Concept-based approach to Voice Disorder Detection](https://mlsanity.com/paper/2507.17799/) (2025)

## Abstract (arXiv)

Recent advances in eXplainable AI (XAI) have provided new insights into how models for vision, language, and tabular data operate. However, few approaches exist for understanding speech models. Existing work focuses on a few spoken language understanding (SLU) tasks, and explanations are difficult to interpret for most users. We introduce a new approach to explain speech classification models. We generate easy-to-interpret explanations via input perturbation on two information levels. 1) Word-level explanations reveal how each word-related audio segment impacts the outcome. 2) Paralinguistic features (e.g., prosody and background noise) answer the counterfactual: ``What would the model prediction be if we edited the audio signal in this way?'' We validate our approach by explaining two state-of-the-art SLU models on two speech classification tasks in English and Italian. Our findings demonstrate that the explanations are faithful to the model's inner workings and plausible to humans. Our method and findings pave the way for future research on interpreting speech models.