# Learning De-identified Representations of Prosody from Raw Audio

arXiv: https://arxiv.org/abs/2107.08248 · HTML: https://mlsanity.com/paper/2107.08248/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 60 references that are in the map.
- First posted on arXiv 17 Jul 2021.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Deep Audio-Visual Speech Recognition](https://mlsanity.com/paper/1809.02108/) (2018)
- [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](https://mlsanity.com/paper/1803.09017/) (2018)
- [Information-Theoretic Probing with Minimum Description Length](https://mlsanity.com/paper/2003.12298/) (2020)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders](https://mlsanity.com/paper/1910.12638/) (2019)
- [Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)](https://mlsanity.com/paper/1906.01815/) (2019)
- [Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron](https://mlsanity.com/paper/1803.09047/) (2018)
- [Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge](https://mlsanity.com/paper/2004.06833/) (2020)
- [Unsupervised Speech Decomposition via Triple Information Bottleneck](https://mlsanity.com/paper/2004.11284/) (2020)
- [Towards Learning a Universal Non-Semantic Representation of Speech](https://mlsanity.com/paper/2002.12764/) (2020)
- [Learning latent representations for style control and transfer in end-to-end speech synthesis](https://mlsanity.com/paper/1812.04342/) (2018)

## Built on by (most cited first, 8 of 8)

- [On the Utility of Self-supervised Models for Prosody-related Tasks](https://mlsanity.com/paper/2210.07185/) (2022)
- [GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech](https://mlsanity.com/paper/2205.07211/) (2022)
- [Disentangling Prosody Representations with Unsupervised Speech Reconstruction](https://mlsanity.com/paper/2212.06972/) (2022)
- [Prosodic Structure Beyond Lexical Content: A Study of Self-Supervised Learning](https://mlsanity.com/paper/2506.02584/) (2025)
- [Disentangling segmental and prosodic factors to non-native speech comprehensibility](https://mlsanity.com/paper/2408.10997/) (2024)
- [CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance](https://mlsanity.com/paper/2509.19883/) (2025)
- [A Variational Framework for Improving Naturalness in Generative Spoken Language Models](https://mlsanity.com/paper/2506.14767/) (2025)
- [Detecting Vocal Fatigue with Neural Embeddings](https://mlsanity.com/paper/2204.03428/) (2022)

## Abstract (arXiv)

We propose a method for learning de-identified prosody representations from raw audio using a contrastive self-supervised signal. Whereas prior work has relied on conditioning models on bottlenecks, we introduce a set of inductive biases that exploit the natural structure of prosody to minimize timbral information and decouple prosody from speaker representations. Despite aggressive downsampling of the input and having no access to linguistic information, our model performs comparably to state-of-the-art speech representations on DAMMP, a new benchmark we introduce for spoken language understanding. We use minimum description length probing to show that our representations have selectively learned the subcomponents of non-timbral prosody, and that the product quantizer naturally disentangles them without using bottlenecks. We derive an information-theoretic definition of speech de-identifiability and use it to demonstrate that our prosody representations are less identifiable than other speech representations.