Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-Speech

• URL: http://arxiv.org/abs/2507.20140v1
• Date: Sun, 27 Jul 2025 06:13:58 GMT
• Title: Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-Speech
• Abstract summary: ZS-TTS has enabled high-fidelity voice synthesis from minimal audio cues, raising significant privacy and ethical concerns.<n>Despite the threats to voice privacy, research to selectively remove the knowledge to replicate unwanted individual voices has not been explored.<n>We propose the first machine unlearning frameworks for ZS-TTS, especially Teacher-Guided Unlearning (TGU)<n>Our proposed methods incorporate randomness to prevent consistent replication of forget speakers' voices, assuring unlearned identities remain untraceable.
• Score: 17.20822861589935
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid advancement of Zero-Shot Text-to-Speech (ZS-TTS) technology has enabled high-fidelity voice synthesis from minimal audio cues, raising significant privacy and ethical concerns. Despite the threats to voice privacy, research to selectively remove the knowledge to replicate unwanted individual voices from pre-trained model parameters has not been explored. In this paper, we address the new challenge of speaker identity unlearning for ZS-TTS systems. To meet this goal, we propose the first machine unlearning frameworks for ZS-TTS, especially Teacher-Guided Unlearning (TGU), designed to ensure the model forgets designated speaker identities while retaining its ability to generate accurate speech for other speakers. Our proposed methods incorporate randomness to prevent consistent replication of forget speakers' voices, assuring unlearned identities remain untraceable. Additionally, we propose a new evaluation metric, speaker-Zero Retrain Forgetting (spk-ZRF). This assesses the model's ability to disregard prompts associated with forgotten speakers, effectively neutralizing its knowledge of these voices. The experiments conducted on the state-of-the-art model demonstrate that TGU prevents the model from replicating forget speakers' voices while maintaining high quality for other speakers. The demo is available at https://speechunlearn.github.io/

Related papers

• Continual Speaker Identity Unlearning with Minimal Interference [28.890263474409696]
  Machine unlearning removes designated concepts or knowledge from pre-trained models.<n>Existing methods, however, quietly assume all unlearning requests arrive at once.<n>We show this assumption breaks state-of-the-art methods, reintroducing the very privacy risk unlearning was meant to eliminate.
  arXiv  Detail & Related papers  (2026-05-25T15:40:04Z)
• Targeted Speaker Poisoning Framework in Zero-Shot Text-to-Speech [42.343691065979215]
  Zero-shot Text-to-Speech (TTS) voice cloning poses severe privacy risks.<n>We formalize this task as Speech Generation Speaker Poisoning (SGSP)<n>We modify trained models to prevent the generation of specific identities while preserving utility for other speakers.
  arXiv  Detail & Related papers  (2026-03-08T09:29:55Z)
• Multi-modal Adversarial Training for Zero-Shot Voice Cloning [9.823246184635103]
  We propose a Transformer encoder-decoder architecture to conditionally discriminate between real and generated speech features. We introduce our novel adversarial training technique by applying it to a FastSpeech2 acoustic model and training on Libriheavy, a large multi-speaker dataset. Our model achieves improvements over the baseline in terms of speech quality and speaker similarity.
  arXiv  Detail & Related papers  (2024-08-28T16:30:41Z)
• Pheme: Efficient and Conversational Speech Generation [52.34331755341856]
  We introduce the Pheme model series that offers compact yet high-performing conversational TTS models. It can be trained efficiently on smaller-scale conversational data, cutting data demands by more than 10x but still matching the quality of the autoregressive TTS models.
  arXiv  Detail & Related papers  (2024-01-05T14:47:20Z)
• Pruning Self-Attention for Zero-Shot Multi-Speaker Text-to-Speech [26.533600745910437]
  We propose an effective pruning method for a transformer known as sparse attention, to improve the TTS model's generalization abilities. We also propose a new differentiable pruning method that allows the model to automatically learn the thresholds.
  arXiv  Detail & Related papers  (2023-08-28T21:25:05Z)
• Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization [61.60501633397704]
  We investigate the emergent abilities of the recently proposed web-scale speech model Whisper, by adapting it to unseen tasks with prompt engineering. We design task-specific prompts, by either leveraging another large-scale model, or simply manipulating the special tokens in the default prompts. Experiments show that our proposed prompts improve performance by 10% to 45% on the three zero-shot tasks, and even outperform SotA supervised models on some datasets.
  arXiv  Detail & Related papers  (2023-05-18T16:32:58Z)
• 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)
• Personalized Speech Enhancement: New Models and Comprehensive Evaluation [27.572537325449158]
  We propose two neural networks for personalized speech enhancement (PSE) models that achieve superior performance to the previously proposed VoiceFilter. We also create test sets that capture a variety of scenarios that users can encounter during video conferencing. Our results show that the proposed models can yield better speech recognition accuracy, speech intelligibility, and perceptual quality than the baseline models.
  arXiv  Detail & Related papers  (2021-10-18T21:21:23Z)
• GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis [6.632254395574993]
  GANSpeech is a high-fidelity multi-speaker TTS model that adopts the adversarial training method to a non-autoregressive multi-speaker TTS model. In the subjective listening tests, GANSpeech significantly outperformed the baseline multi-speaker FastSpeech and FastSpeech2 models.
  arXiv  Detail & Related papers  (2021-06-29T08:15:30Z)
• Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation [63.561944239071615]
  StyleSpeech is a new TTS model which synthesizes high-quality speech and adapts to new speakers. With SALN, our model effectively synthesizes speech in the style of the target speaker even from single speech audio. We extend it to Meta-StyleSpeech by introducing two discriminators trained with style prototypes, and performing episodic training.
  arXiv  Detail & Related papers  (2021-06-06T15:34:11Z)
• Voice Cloning: a Multi-Speaker Text-to-Speech Synthesis Approach based on Transfer Learning [0.802904964931021]
  The proposed approach has the goal to overcome these limitations trying to obtain a system which is able to model a multi-speaker acoustic space. This allows the generation of speech audio similar to the voice of different target speakers, even if they were not observed during the training phase.
  arXiv  Detail & Related papers  (2021-02-10T18:43:56Z)
• Speaker De-identification System using Autoencoders and Adversarial Training [58.720142291102135]
  We propose a speaker de-identification system based on adversarial training and autoencoders. Experimental results show that combining adversarial learning and autoencoders increase the equal error rate of a speaker verification system.
  arXiv  Detail & Related papers  (2020-11-09T19:22:05Z)
• Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation [125.59372403631006]
  We propose a semi-supervised learning approach for multi-speaker text-to-speech (TTS) A multi-speaker TTS model can learn from the untranscribed audio via the proposed encoder-decoder framework with discrete speech representation. We found the model can benefit from the proposed semi-supervised learning approach even when part of the unpaired speech data is noisy.
  arXiv  Detail & Related papers  (2020-05-16T15:47:11Z)

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.