Autoregressive Diffusion Transformer for Text-to-Speech Synthesis

• URL: http://arxiv.org/abs/2406.05551v1
• Date: Sat, 8 Jun 2024 18:57:13 GMT
• Title: Autoregressive Diffusion Transformer for Text-to-Speech Synthesis
• Authors: Zhijun Liu, Shuai Wang, Sho Inoue, Qibing Bai, Haizhou Li,
• Abstract summary: We propose encoding audio as vector sequences in continuous space $mathbb Rd$ and autoregressively generating these sequences. High-bitrate continuous speech representation enables almost flawless reconstruction, allowing our model to achieve nearly perfect speech editing.
• Score: 39.32761051774537
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Audio language models have recently emerged as a promising approach for various audio generation tasks, relying on audio tokenizers to encode waveforms into sequences of discrete symbols. Audio tokenization often poses a necessary compromise between code bitrate and reconstruction accuracy. When dealing with low-bitrate audio codes, language models are constrained to process only a subset of the information embedded in the audio, which in turn restricts their generative capabilities. To circumvent these issues, we propose encoding audio as vector sequences in continuous space $\mathbb R^d$ and autoregressively generating these sequences using a decoder-only diffusion transformer (ARDiT). Our findings indicate that ARDiT excels in zero-shot text-to-speech and exhibits performance that compares to or even surpasses that of state-of-the-art models. High-bitrate continuous speech representation enables almost flawless reconstruction, allowing our model to achieve nearly perfect speech editing. Our experiments reveal that employing Integral Kullback-Leibler (IKL) divergence for distillation at each autoregressive step significantly boosts the perceived quality of the samples. Simultaneously, it condenses the iterative sampling process of the diffusion model into a single step. Furthermore, ARDiT can be trained to predict several continuous vectors in one step, significantly reducing latency during sampling. Impressively, one of our models can generate $170$ ms of $24$ kHz speech per evaluation step with minimal degradation in performance. Audio samples are available at http://ardit-tts.github.io/ .

Related papers

• VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment [101.2489492032816]
  VALL-E R is a robust and efficient zero-shot Text-to-Speech system. This research has the potential to be applied to meaningful projects, including the creation of speech for those affected by aphasia.
  arXiv  Detail & Related papers  (2024-06-12T04:09:44Z)
• TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition [51.565319173790314]
  TokenSplit is a sequence-to-sequence encoder-decoder model that uses the Transformer architecture. We show that our model achieves excellent performance in terms of separation, both with or without transcript conditioning. We also measure the automatic speech recognition (ASR) performance and provide audio samples of speech synthesis to demonstrate the additional utility of our model.
  arXiv  Detail & Related papers  (2023-08-21T01:52:01Z)
• From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion [84.138804145918]
  Deep generative models can generate high-fidelity audio conditioned on various types of representations. These models are prone to generate audible artifacts when the conditioning is flawed or imperfect. We propose a high-fidelity multi-band diffusion-based framework that generates any type of audio modality from low-bitrate discrete representations.
  arXiv  Detail & Related papers  (2023-08-02T22:14:29Z)
• AudioGen: Textually Guided Audio Generation [116.57006301417306]
  We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive model that generates audio samples conditioned on text inputs.
  arXiv  Detail & Related papers  (2022-09-30T10:17:05Z)
• FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis [77.06890315052563]
  We propose FastLTS, a non-autoregressive end-to-end model which can directly synthesize high-quality speech audios from unconstrained talking videos with low latency. Experiments show that our model achieves $19.76times$ speedup for audio generation compared with the current autoregressive model on input sequences of 3 seconds.
  arXiv  Detail & Related papers  (2022-07-08T10:10:39Z)
• RAVE: A variational autoencoder for fast and high-quality neural audio synthesis [2.28438857884398]
  We introduce a Realtime Audio Variational autoEncoder (RAVE) allowing both fast and high-quality audio waveform synthesis. We show that our model is the first able to generate 48kHz audio signals, while simultaneously running 20 times faster than real-time on a standard laptop CPU.
  arXiv  Detail & Related papers  (2021-11-09T09:07:30Z)
• Transformer Transducer: One Model Unifying Streaming and Non-streaming Speech Recognition [16.082949461807335]
  We present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. We show that we can run this model in a Y-model architecture with the top layers running in parallel in low latency and high latency modes. This allows us to have streaming speech recognition results with limited latency and delayed speech recognition results with large improvements in accuracy.
  arXiv  Detail & Related papers  (2020-10-07T05:58:28Z)
• Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss [14.755108017449295]
  We present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks based on self-attention are used to encode both audio and label sequences independently. We present results on the LibriSpeech dataset showing that limiting the left context for self-attention makes decoding computationally tractable for streaming.
  arXiv  Detail & Related papers  (2020-02-07T00:04:04Z)

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.