Source-linked AI summary

Diff-TTS: A Denoising Diffusion Model for Text-to-Speech

Myeonghun Jeong, Hyeongju Kim, Sung Jun Cheon, Byoung Jin Choi, Nam Soo Kim

arXiv:2104.01409v1eess.AScs.AIcs.SD

TL;DR

Neural TTS still faces challenges in naturalness, inference efficiency, and architectural limitations. Diff-TTS addresses these issues with a non-autoregressive denoising diffusion model, likelihood-based training, and accelerated sampling. It achieves high-fidelity synthesis with fewer parameters and inference up to 28 times faster than real time.

  • Problem

    Neural TTS models still require improvements in naturalness and architectural efficiency, while autoregressive systems have inference-time and robustness limitations and flow-based systems can be parameter-inefficient.

  • Method

    Diff-TTS transforms Gaussian noise into text-conditioned mel-spectrograms through denoising diffusion, trains with a log-likelihood objective, and uses accelerated sampling for faster synthesis.

  • Results

    28 times faster than real time, Diff-TTS achieves faster-than-real-time inference while maintaining higher MOS than Tacotron2 at γ = 57.

  • Takeaways & Limitations

    Diff-TTS provides controllable, high-fidelity non-AR speech synthesis with fewer parameters and a user-adjustable quality–speed trade-off.

  • Takeaways & Limitations

    Flow-based TTS models are described as parameter-inefficient because of architectural constraints imposed by normalizing flows.

Abstract

from arXiv · show

Although neural text-to-speech (TTS) models have attracted a lot of attention and succeeded in generating human-like speech, there is still room for improvements to its naturalness and architectural efficiency. In this work, we propose a novel non-autoregressive TTS model, namely Diff-TTS, which achieves highly natural and efficient speech synthesis. Given the text, Diff-TTS exploits a denoising diffusion framework to transform the noise signal into a mel-spectrogram via diffusion time steps. In order to learn the mel-spectrogram distribution conditioned on the text, we present a likelihood-based optimization method for TTS. Furthermore, to boost up the inference speed, we leverage the accelerated sampling method that allows Diff-TTS to generate raw waveforms much faster without significantly degrading perceptual quality. Through experiments, we verified that Diff-TTS generates 28 times faster than the real-time with a single NVIDIA 2080Ti GPU.

1. Introduction

Diff-TTS is a non-autoregressive TTS model that applies denoising diffusion to improve synthesis quality and efficiency while avoiding architectural constraints of flow-based models. It combines likelihood-based training, accelerated sampling, and prosody control.

  • Scope: The model targets acoustic modeling by converting text into mel-spectrograms before waveform generation by a vocoder.The paper focuses on the acoustic-modeling component of a standard neural TTS pipeline.
  • Contributions: Diff-TTS uses log-likelihood-based optimization to train without auxiliary loss functions or model-architecture constraints.The denoising diffusion framework supports stable optimization while preserving freedom in architecture choices.
  • Contributions: Diff-TTS applies a denoising diffusion probabilistic model to non-AR mel-spectrogram generation.The model is presented as the first DDPM applied to non-AR TTS.
  • Contributions: Diff-TTS achieves high-fidelity synthesis with half the parameters of Tacotron2 and Glow-TTS, measured by Mean Opinion Score.This addresses efficiency alongside synthesis quality.
  • Contributions: Accelerated sampling lets users trade sample quality against inference speed according to available computational resources.The method reduces reverse transitions without significantly degrading sample quality and achieves faster-than-real-time inference.
  • Contributions: Diff-TTS controls pitch variability through latent-space and additive-noise variances scaled by a temperature term.The paper analyzes this mechanism as a form of speech-prosody control.

2. Diff-TTS

Diff-TTS uses a denoising diffusion process to generate text-conditioned mel-spectrograms, with reverse transitions recovering speech features from Gaussian noise. Accelerated sampling reduces reverse transitions while preserving high-fidelity mel-spectrogram generation, supported by a text-conditioned architecture.

  • Denoising diffusion model for TTS: Diff-TTS transforms mel-spectrograms into Gaussian noise through Markov diffusion transitions and reverses this process to generate text-conditioned mel-spectrograms.The forward process uses a predefined variance schedule, while the reverse process restores mel-spectrograms from noise.
  • Denoising diffusion model for TTS: The reverse process maximizes the conditional mel-spectrogram log-likelihood, using an L1 loss between predicted and sampled Gaussian noise without auxiliary losses.During inference, the model predicts the noise added at each forward transition and removes the corrupted component iteratively.
  • Accelerated Sampling: Accelerated sampling selects a shorter reverse-time subsequence using decimation factor γ, reducing reverse transitions without model retraining or significant sample-quality deterioration.The new reverse path periodically selects transitions from the original trajectory.
  • Accelerated Sampling: Accelerated sampling produces high-fidelity mel-spectrograms over the subsequence τ and increases inference speed for mel-spectrogram generation.This method is intended to improve synthesis speed while preserving sample quality.
  • Model Architecture: The Diff-TTS architecture combines text encoding, diffusion-step encoding, duration prediction, length regulation, and decoding to produce Gaussian noise conditioned on phoneme sequences and diffusion time-steps.The encoder provides contextual phoneme information, while the length regulator expands phoneme embeddings to match mel-spectrogram sequence length.

3. Experiments

Experiments evaluate Diff-TTS for audio quality, model size, inference speed, and prosody controllability. The results show high-quality synthesis with fewer parameters, substantially faster-than-real-time generation, and temperature-controlled prosodic diversity.

  • Audio quality and model size: Diff-TTS achieved high-fidelity audio while requiring about 53% fewer parameters than Tacotron2 and Glow-TTS.The model required the fewest parameters among the compared systems.
  • Audio quality and model size: Accelerated sampling preserved speech quality comparably to Tacotron2 and Glow-TTS, with degradation at γ = 57 reported as not significant.The best MOS occurred with 400 diffusion time steps, while accelerated settings remained practical for synthesis.
  • Inference speed: Accelerated sampling gave Diff-TTS an RTF of 0.035 at γ = 57 while maintaining higher MOS than Tacotron2.RTF measures the time required to synthesize one second of waveform; evaluations used 500 test sentences on one NVIDIA 2080Ti GPU.
  • Inference speed: Diff-TTS ran 28 times faster than real-time, although Glow-TTS remained faster on the same comparison.The accelerated sampler enables a quality–speed trade-off based on available computational resources.
  • Variability and controllability: Increasing the temperature term η from 0.2 to 0.6 produced more diverse speech while maintaining speech quality.Temperature scaling modifies latent-space and additive-noise variances, allowing prosody variability to be controlled without retraining.

4. Conclusions

Diff-TTS is presented as a controllable, high-fidelity non-autoregressive diffusion model for mel-spectrogram generation, with improved quality, efficiency, speed control, and prosodic variability.

  • Diff-TTS outperforms Tacotron2 and Glow-TTS in synthesis quality with fewer parameters.The model achieves high-fidelity audio according to Mean Opinion Score while using half the parameters of both systems.
  • Accelerated sampling lets users trade sample quality for inference speed, reaching up to 28 times faster than real-time without significantly degrading audio quality.
  • Multiplying a temperature term gives Diff-TTS control over speech prosodic variability.
  • Diff-TTS is identified as the first diffusion generative model for non-autoregressive mel-spectrogram generation.
  • The authors propose extending Diff-TTS to multi-speaker and emotional TTS in future work.
Loading 2104.01409v1…