On the Semantic Latent Space of Diffusion-Based Text-to-Speech Models
- URL: http://arxiv.org/abs/2402.12423v2
- Date: Tue, 4 Jun 2024 11:03:57 GMT
- Title: On the Semantic Latent Space of Diffusion-Based Text-to-Speech Models
- Authors: Miri Varshavsky-Hassid, Roy Hirsch, Regev Cohen, Tomer Golany, Daniel Freedman, Ehud Rivlin,
- Abstract summary: We explore the latent space of frozen TTS models, which is composed of the latent bottleneck activations of the DDM's denoiser.
We identify that this space contains rich semantic information, and outline several novel methods for finding semantic directions within it, both supervised and unsupervised.
We demonstrate how these enable off-the-shelf audio editing, without any further training, architectural changes or data requirements.
- Score: 15.068637971987224
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The incorporation of Denoising Diffusion Models (DDMs) in the Text-to-Speech (TTS) domain is rising, providing great value in synthesizing high quality speech. Although they exhibit impressive audio quality, the extent of their semantic capabilities is unknown, and controlling their synthesized speech's vocal properties remains a challenge. Inspired by recent advances in image synthesis, we explore the latent space of frozen TTS models, which is composed of the latent bottleneck activations of the DDM's denoiser. We identify that this space contains rich semantic information, and outline several novel methods for finding semantic directions within it, both supervised and unsupervised. We then demonstrate how these enable off-the-shelf audio editing, without any further training, architectural changes or data requirements. We present evidence of the semantic and acoustic qualities of the edited audio, and provide supplemental samples: https://latent-analysis-grad-tts.github.io/speech-samples/.
Related papers
- CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens [49.569695524535454]
We propose to represent speech with supervised semantic tokens, which are derived from a multilingual speech recognition model by inserting vector quantization into the encoder.
Based on the tokens, we further propose a scalable zero-shot TTS synthesizer, CosyVoice, which consists of an LLM for text-to-token generation and a conditional flow matching model for token-to-speech synthesis.
arXiv Detail & Related papers (2024-07-07T15:16:19Z) - An Empirical Study of Speech Language Models for Prompt-Conditioned Speech Synthesis [45.558316325252335]
Speech language models (LMs) are promising for high-quality speech synthesis through in-context learning.
We study how the synthesized audio is controlled by the prompt and content.
arXiv Detail & Related papers (2024-03-19T03:22:28Z) - Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt [50.25271407721519]
We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language.
We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation.
Experiments show that our model achieves favorable controlling ability and audio quality.
arXiv Detail & Related papers (2024-03-18T13:39:05Z) - High-Fidelity Speech Synthesis with Minimal Supervision: All Using
Diffusion Models [56.00939852727501]
Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech representations.
Non-autoregressive framework enhances controllability, and duration diffusion model enables diversified prosodic expression.
arXiv Detail & Related papers (2023-09-27T09:27:03Z) - EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech
Resynthesis [49.04496602282718]
We introduce Expresso, a high-quality expressive speech dataset for textless speech synthesis.
This dataset includes both read speech and improvised dialogues rendered in 26 spontaneous expressive styles.
We evaluate resynthesis quality with automatic metrics for different self-supervised discrete encoders.
arXiv Detail & Related papers (2023-08-10T17:41:19Z) - A Vector Quantized Approach for Text to Speech Synthesis on Real-World
Spontaneous Speech [94.64927912924087]
We train TTS systems using real-world speech from YouTube and podcasts.
Recent Text-to-Speech architecture is designed for multiple code generation and monotonic alignment.
We show thatRecent Text-to-Speech architecture outperforms existing TTS systems in several objective and subjective measures.
arXiv Detail & Related papers (2023-02-08T17:34:32Z) - Self-Supervised Learning for Speech Enhancement through Synthesis [5.924928860260821]
We propose a denoising vocoder (DeVo) approach, where a vocoder accepts noisy representations and learns to directly synthesize clean speech.
We demonstrate a causal version capable of running on streaming audio with 10ms latency and minimal performance degradation.
arXiv Detail & Related papers (2022-11-04T16:06:56Z) - Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE [36.50265124324876]
We propose a novel unsupervised text-to-speech acoustic model training scheme, named UTTS, which does not require text-audio pairs.
The framework offers a flexible choice of a speaker's duration model, timbre feature (identity) and content for TTS inference.
Experiments demonstrate that UTTS can synthesize speech of high naturalness and intelligibility measured by human and objective evaluations.
arXiv Detail & Related papers (2022-06-06T11:51:22Z) - Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement
by Re-Synthesis [67.73554826428762]
We propose a novel audio-visual speech enhancement framework for high-fidelity telecommunications in AR/VR.
Our approach leverages audio-visual speech cues to generate the codes of a neural speech, enabling efficient synthesis of clean, realistic speech from noisy signals.
arXiv Detail & Related papers (2022-03-31T17:57:10Z) - Enhancing audio quality for expressive Neural Text-to-Speech [8.199224915764672]
We present a set of techniques that can be leveraged to enhance the signal quality of a highly-expressive voice without the use of additional data.
We show that, when combined, these techniques greatly closed the gap in perceived naturalness between the baseline system and recordings by 39% in terms of MUSHRA scores for an expressive celebrity voice.
arXiv Detail & Related papers (2021-08-13T14:32:39Z)
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.