DiTTo-TTS: Efficient and Scalable Zero-Shot Text-to-Speech with Diffusion Transformer

• URL: http://arxiv.org/abs/2406.11427v1
• Date: Mon, 17 Jun 2024 11:25:57 GMT
• Title: DiTTo-TTS: Efficient and Scalable Zero-Shot Text-to-Speech with Diffusion Transformer
• Authors: Keon Lee, Dong Won Kim, Jaehyeon Kim, Jaewoong Cho,
• Abstract summary: We present an efficient and scalable Diffusion Transformer (DiT) that utilizes off-the-shelf pre-trained text and speech encoders. Our approach addresses the challenge of text-speech alignment via cross-attention mechanisms with the prediction of the total length of speech representations. We scale the training dataset and the model size to 82K hours and 790M parameters, respectively.
• Score: 9.032701216955497
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large-scale diffusion models have shown outstanding generative abilities across multiple modalities including images, videos, and audio. However, text-to-speech (TTS) systems typically involve domain-specific modeling factors (e.g., phonemes and phoneme-level durations) to ensure precise temporal alignments between text and speech, which hinders the efficiency and scalability of diffusion models for TTS. In this work, we present an efficient and scalable Diffusion Transformer (DiT) that utilizes off-the-shelf pre-trained text and speech encoders. Our approach addresses the challenge of text-speech alignment via cross-attention mechanisms with the prediction of the total length of speech representations. To achieve this, we enhance the DiT architecture to suit TTS and improve the alignment by incorporating semantic guidance into the latent space of speech. We scale the training dataset and the model size to 82K hours and 790M parameters, respectively. Our extensive experiments demonstrate that the large-scale diffusion model for TTS without domain-specific modeling not only simplifies the training pipeline but also yields superior or comparable zero-shot performance to state-of-the-art TTS models in terms of naturalness, intelligibility, and speaker similarity. Our speech samples are available at https://ditto-tts.github.io.

Related papers

• DPI-TTS: Directional Patch Interaction for Fast-Converging and Style Temporal Modeling in Text-to-Speech [43.45691362372739]
  We propose a method called Directional Patch Interaction for Text-to-Speech (DPI-TTS) DPI-TTS employs a low-to-high frequency, frame-by-frame progressive inference approach that aligns more closely with acoustic properties. Experimental results demonstrate that our method increases the training speed by nearly 2 times and significantly outperforms the baseline models.
  arXiv  Detail & Related papers  (2024-09-18T09:36:55Z)
• SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models [64.40250409933752]
  We build upon our previous publication by implementing a simple and efficient non-autoregressive (NAR) TTS framework, termed SimpleSpeech 2. SimpleSpeech 2 effectively combines the strengths of both autoregressive (AR) and non-autoregressive (NAR) methods. We show a significant improvement in generation performance and generation speed compared to our previous work and other state-of-the-art (SOTA) large-scale TTS models.
  arXiv  Detail & Related papers  (2024-08-25T17:07:39Z)
• DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability [7.005068872406135]
  Diffusion-based EXpressive TTS (DEX-TTS) is an acoustic model designed for reference-based speech synthesis with enhanced style representations. DEX-TTS includes encoders and adapters to handle styles extracted from reference speech. In addition, we introduce overlapping patchify and convolution-frequency patch embedding strategies to improve DiT-based diffusion networks for TTS.
  arXiv  Detail & Related papers  (2024-06-27T12:39:55Z)
• NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models [127.47252277138708]
  We propose NaturalSpeech 3, a TTS system with factorized diffusion models to generate natural speech in a zero-shot way. Specifically, we design a neural with factorized vector quantization (FVQ) to disentangle speech waveform into subspaces of content, prosody, timbre, and acoustic details. Experiments show that NaturalSpeech 3 outperforms the state-of-the-art TTS systems on quality, similarity, prosody, and intelligibility.
  arXiv  Detail & Related papers  (2024-03-05T16:35:25Z)
• StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models [19.029030168939354]
  StyleTTS 2 is a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 surpasses human recordings on the single-speaker LJSpeech dataset and matches it on the multispeaker VCTK dataset as judged by native English speakers. This work achieves the first human-level TTS on both single and multispeaker datasets, showcasing the potential of style diffusion and adversarial training with large SLMs.
  arXiv  Detail & Related papers  (2023-06-13T11:04:43Z)
• Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias [71.94109664001952]
  Mega-TTS is a novel zero-shot TTS system that is trained with large-scale wild data. We show that Mega-TTS surpasses state-of-the-art TTS systems on zero-shot TTS speech editing, and cross-lingual TTS tasks.
  arXiv  Detail & Related papers  (2023-06-06T08:54:49Z)
• NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers [90.83782600932567]
  We develop NaturalSpeech 2, a TTS system that leverages a neural audio predictor with residual vectorizers to get the quantized latent vectors. We scale NaturalSpeech 2 to large-scale datasets with 44K hours of speech and singing data and evaluate its voice quality on unseen speakers. NaturalSpeech 2 outperforms previous TTS systems by a large margin in terms of prosody/timbre similarity, synthesis, and voice quality in a zero-shot setting.
  arXiv  Detail & Related papers  (2023-04-18T16:31:59Z)
• Any-speaker Adaptive Text-To-Speech Synthesis with Diffusion Models [65.28001444321465]
  Grad-StyleSpeech is an any-speaker adaptive TTS framework based on a diffusion model. It can generate highly natural speech with extremely high similarity to target speakers' voice, given a few seconds of reference speech. It significantly outperforms speaker-adaptive TTS baselines on English benchmarks.
  arXiv  Detail & Related papers  (2022-11-17T07:17:24Z)
• MultiSpeech: Multi-Speaker Text to Speech with Transformer [145.56725956639232]
  Transformer-based text to speech (TTS) model (e.g., Transformer TTSciteli 2019neural, FastSpeechciteren 2019fastspeech) has shown the advantages of training and inference efficiency over RNN-based model. We develop a robust and high-quality multi-speaker Transformer TTS system called MultiSpeech, with several specially designed components/techniques to improve text-to-speech alignment.
  arXiv  Detail & Related papers  (2020-06-08T15:05:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.