# A Variational Framework for Improving Naturalness in Generative Spoken Language Models

arXiv: https://arxiv.org/abs/2506.14767 · HTML: https://mlsanity.com/paper/2506.14767/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 48 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Builds on (most cited first, 30 of 34)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search](https://mlsanity.com/paper/2005.11129/) (2020)
- [Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing](https://mlsanity.com/paper/1903.10145/) (2019)
- [Text-Free Prosody-Aware Generative Spoken Language Modeling](https://mlsanity.com/paper/2109.03264/) (2021)
- [CREPE: A Convolutional Representation for Pitch Estimation](https://mlsanity.com/paper/1802.06182/) (2018)
- [The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling](https://mlsanity.com/paper/2011.11588/) (2020)
- [Textually Pretrained Speech Language Models](https://mlsanity.com/paper/2305.13009/) (2023)
- [Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks](https://mlsanity.com/paper/2309.07937/) (2023)
- [S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation](https://mlsanity.com/paper/2005.11437/) (2020)

## Built on by (most cited first, 1 of 1)

- [Speak Your Mind: The Speech Continuation Task as a Probe of Voice-Based Model Bias](https://mlsanity.com/paper/2509.22061/) (2025)

## Abstract (arXiv)

The success of large language models in text processing has inspired their adaptation to speech modeling. However, since speech is continuous and complex, it is often discretized for autoregressive modeling. Speech tokens derived from self-supervised models (known as semantic tokens) typically focus on the linguistic aspects of speech but neglect prosodic information. As a result, models trained on these tokens can generate speech with reduced naturalness. Existing approaches try to fix this by adding pitch features to the semantic tokens. However, pitch alone cannot fully represent the range of paralinguistic attributes, and selecting the right features requires careful hand-engineering. To overcome this, we propose an end-to-end variational approach that automatically learns to encode these continuous speech attributes to enhance the semantic tokens. Our approach eliminates the need for manual extraction and selection of paralinguistic features. Moreover, it produces preferred speech continuations according to human raters. Code, samples and models are available at https://github.com/b04901014/vae-gslm.