CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Xiang, Bu, Fan, Mehrish, Ambuj, Li, Yingting, Han, Jiale, Cheng, Bo, Poria, Soujanya
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916186564853760
author Li, Xiang
Bu, Fan
Mehrish, Ambuj
Li, Yingting
Han, Jiale
Cheng, Bo
Poria, Soujanya
author_facet Li, Xiang
Bu, Fan
Mehrish, Ambuj
Li, Yingting
Han, Jiale
Cheng, Bo
Poria, Soujanya
contents Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech synthesis. Yet, the efficiency of multi-step sampling in Diffusion Models presents challenges. Efforts have been made to integrate GANs with DMs, speeding up inference by approximating denoising distributions, but this introduces issues with model convergence due to adversarial training. To overcome this, we introduce CM-TTS, a novel architecture grounded in consistency models (CMs). Drawing inspiration from continuous-time diffusion models, CM-TTS achieves top-quality speech synthesis in fewer steps without adversarial training or pre-trained model dependencies. We further design weighted samplers to incorporate different sampling positions into model training with dynamic probabilities, ensuring unbiased learning throughout the entire training process. We present a real-time mel-spectrogram generation consistency model, validated through comprehensive evaluations. Experimental results underscore CM-TTS's superiority over existing single-step speech synthesis systems, representing a significant advancement in the field.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00569
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models
Li, Xiang
Bu, Fan
Mehrish, Ambuj
Li, Yingting
Han, Jiale
Cheng, Bo
Poria, Soujanya
Sound
Computation and Language
Audio and Speech Processing
Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech synthesis. Yet, the efficiency of multi-step sampling in Diffusion Models presents challenges. Efforts have been made to integrate GANs with DMs, speeding up inference by approximating denoising distributions, but this introduces issues with model convergence due to adversarial training. To overcome this, we introduce CM-TTS, a novel architecture grounded in consistency models (CMs). Drawing inspiration from continuous-time diffusion models, CM-TTS achieves top-quality speech synthesis in fewer steps without adversarial training or pre-trained model dependencies. We further design weighted samplers to incorporate different sampling positions into model training with dynamic probabilities, ensuring unbiased learning throughout the entire training process. We present a real-time mel-spectrogram generation consistency model, validated through comprehensive evaluations. Experimental results underscore CM-TTS's superiority over existing single-step speech synthesis systems, representing a significant advancement in the field.
title CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models
topic Sound
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2404.00569