# What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis

arXiv: https://arxiv.org/abs/2107.00439 · HTML: https://mlsanity.com/paper/2107.00439/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 104 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 30 of 59)

- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [Analysis Methods in Neural Language Processing: A Survey](https://mlsanity.com/paper/1812.08951/) (2018)
- [Information-Theoretic Probing with Minimum Description Length](https://mlsanity.com/paper/2003.12298/) (2020)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [Information-Theoretic Probing for Linguistic Structure](https://mlsanity.com/paper/2004.03061/) (2020)
- [Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders](https://mlsanity.com/paper/1910.12638/) (2019)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [Synthesizing the preferred inputs for neurons in neural networks via deep generator networks](https://mlsanity.com/paper/1605.09304/) (2016)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks](https://mlsanity.com/paper/1903.05987/) (2019)
- [What do Neural Machine Translation Models Learn about Morphology?](https://mlsanity.com/paper/1704.03471/) (2017)
- [Visual Interpretability for Deep Learning: a Survey](https://mlsanity.com/paper/1802.00614/) (2018)
- [Dissecting Contextual Word Embeddings: Architecture and Representation](https://mlsanity.com/paper/1808.08949/) (2018)
- [What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models](https://mlsanity.com/paper/1812.09355/) (2018)
- [On the Effect of Dropping Layers of Pre-trained Transformer Models](https://mlsanity.com/paper/2004.03844/) (2020)

## Built on by (most cited first, 9 of 9)

- [Discovering Salient Neurons in Deep NLP Models](https://mlsanity.com/paper/2206.13288/) (2022)
- [What Do Speech Foundation Models Not Learn About Speech?](https://mlsanity.com/paper/2410.12948/) (2024)
- [Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation](https://mlsanity.com/paper/2511.21517/) (2025)
- [Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models](https://mlsanity.com/paper/2406.02285/) (2024)
- [Different Speech Translation Models Encode and Translate Speaker Gender Differently](https://mlsanity.com/paper/2506.02172/) (2025)
- [Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models](https://mlsanity.com/paper/2506.10855/) (2025)
- [Speech foundation models in healthcare: Effect of layer selection on pathological speech feature prediction](https://mlsanity.com/paper/2402.01796/) (2024)
- [From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models](https://mlsanity.com/paper/2506.01133/) (2025)
- [Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers](https://mlsanity.com/paper/2506.21712/) (2025)

## Abstract (arXiv)

Deep neural networks are inherently opaque and challenging to interpret. Unlike hand-crafted feature-based models, we struggle to comprehend the concepts learned and how they interact within these models. This understanding is crucial not only for debugging purposes but also for ensuring fairness in ethical decision-making. In our study, we conduct a post-hoc functional interpretability analysis of pretrained speech models using the probing framework [1]. Specifically, we analyze utterance-level representations of speech models trained for various tasks such as speaker recognition and dialect identification. We conduct layer and neuron-wise analyses, probing for speaker, language, and channel properties. Our study aims to answer the following questions: i) what information is captured within the representations? ii) how is it represented and distributed? and iii) can we identify a minimal subset of the network that possesses this information? Our results reveal several novel findings, including: i) channel and gender information are distributed across the network, ii) the information is redundantly available in neurons with respect to a task, iii) complex properties such as dialectal information are encoded only in the task-oriented pretrained network, iv) and is localised in the upper layers, v) we can extract a minimal subset of neurons encoding the pre-defined property, vi) salient neurons are sometimes shared between properties, vii) our analysis highlights the presence of biases (for example gender) in the network. Our cross-architectural comparison indicates that: i) the pretrained models capture speaker-invariant information, and ii) CNN models are competitive with Transformer models in encoding various understudied properties.