# Boosting Diffusion Model for Spectrogram Up-sampling in Text-to-speech: An Empirical Study

arXiv: https://arxiv.org/abs/2406.04633 · HTML: https://mlsanity.com/paper/2406.04633/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 29 of its 37 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 29 of 29)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [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)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers](https://mlsanity.com/paper/2304.09116/) (2023)
- [NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models](https://mlsanity.com/paper/2403.03100/) (2024)
- [AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling](https://mlsanity.com/paper/2402.12226/) (2024)
- [Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling](https://mlsanity.com/paper/2303.03926/) (2023)
- [NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality](https://mlsanity.com/paper/2205.04421/) (2022)
- [Audiobox: Unified Audio Generation with Natural Language Prompts](https://mlsanity.com/paper/2312.15821/) (2023)
- [SoundStorm: Efficient Parallel Audio Generation](https://mlsanity.com/paper/2305.09636/) (2023)
- [Better speech synthesis through scaling](https://mlsanity.com/paper/2305.07243/) (2023)
- [The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing](https://mlsanity.com/paper/2311.01410/) (2023)
- [Bespoke Solvers for Generative Flow Models](https://mlsanity.com/paper/2310.19075/) (2023)
- [From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion](https://mlsanity.com/paper/2308.02560/) (2023)
- [DelightfulTTS 2: End-to-End Speech Synthesis with Adversarial Vector-Quantized Auto-Encoders](https://mlsanity.com/paper/2207.04646/) (2022)
- [CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models](https://mlsanity.com/paper/2404.00569/) (2024)
- [Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like](https://mlsanity.com/paper/2402.07383/) (2024)
- [FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model](https://mlsanity.com/paper/2303.02939/) (2023)
- [On the Semantic Latent Space of Diffusion-Based Text-to-Speech Models](https://mlsanity.com/paper/2402.12423/) (2024)

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

- [Next Tokens Denoising for Speech Synthesis](https://mlsanity.com/paper/2507.22746/) (2025)

## Abstract (arXiv)

Scaling text-to-speech (TTS) with autoregressive language model (LM) to large-scale datasets by quantizing waveform into discrete speech tokens is making great progress to capture the diversity and expressiveness in human speech, but the speech reconstruction quality from discrete speech token is far from satisfaction depending on the compressed speech token compression ratio. Generative diffusion models trained with score-matching loss and continuous normalized flow trained with flow-matching loss have become prominent in generation of images as well as speech. LM based TTS systems usually quantize speech into discrete tokens and generate these tokens autoregressively, and finally use a diffusion model to up sample coarse-grained speech tokens into fine-grained codec features or mel-spectrograms before reconstructing into waveforms with vocoder, which has a high latency and is not realistic for real time speech applications. In this paper, we systematically investigate varied diffusion models for up sampling stage, which is the main bottleneck for streaming synthesis of LM and diffusion-based architecture, we present the model architecture, objective and subjective metrics to show quality and efficiency improvement.