# Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition

arXiv: https://arxiv.org/abs/1907.04224 · HTML: https://mlsanity.com/paper/1907.04224/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2019.

## Built on by (most cited first, 16 of 16)

- [PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition](https://mlsanity.com/paper/2106.05933/) (2021)
- [Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques](https://mlsanity.com/paper/2104.13225/) (2021)
- [N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition](https://mlsanity.com/paper/2306.02902/) (2023)
- [Wave to Syntax: Probing spoken language models for syntax](https://mlsanity.com/paper/2305.18957/) (2023)
- [Arabic Speech Recognition by End-to-End, Modular Systems and Human](https://mlsanity.com/paper/2101.08454/) (2021)
- [PANCETTA: Phoneme Aware Neural Completion to Elicit Tongue Twisters Automatically](https://mlsanity.com/paper/2209.06275/) (2022)
- [Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations](https://mlsanity.com/paper/2509.15655/) (2025)
- [Quran Recitation Recognition using End-to-End Deep Learning](https://mlsanity.com/paper/2305.07034/) (2023)
- [VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System](https://mlsanity.com/paper/2310.11069/) (2023)
- [Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition](https://mlsanity.com/paper/2111.04194/) (2021)
- [End-to-End Automatic Speech Recognition model for the Sudanese Dialect](https://mlsanity.com/paper/2212.10826/) (2022)
- [Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribution](https://mlsanity.com/paper/2506.02181/) (2025)
- [Probing the Information Encoded in Neural-based Acoustic Models of Automatic Speech Recognition Systems](https://mlsanity.com/paper/2402.19443/) (2024)
- [Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic](https://mlsanity.com/paper/2507.13977/) (2025)
- [Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs](https://mlsanity.com/paper/2508.17914/) (2025)
- [Categorize Early, Integrate Late: Divergent Processing Strategies in Automatic Speech Recognition](https://mlsanity.com/paper/2601.06972/) (2026)

## Abstract (arXiv)

End-to-end neural network systems for automatic speech recognition (ASR) are trained from acoustic features to text transcriptions. In contrast to modular ASR systems, which contain separately-trained components for acoustic modeling, pronunciation lexicon, and language modeling, the end-to-end paradigm is both conceptually simpler and has the potential benefit of training the entire system on the end task. However, such neural network models are more opaque: it is not clear how to interpret the role of different parts of the network and what information it learns during training. In this paper, we analyze the learned internal representations in an end-to-end ASR model. We evaluate the representation quality in terms of several classification tasks, comparing phonemes and graphemes, as well as different articulatory features. We study two languages (English and Arabic) and three datasets, finding remarkable consistency in how different properties are represented in different layers of the deep neural network.