相关论文: Voice "Cloning" is Style Transfer

While many recent any-to-any voice conversion models succeed in transferring some target speech's style information to the converted speech, they still lack the ability to faithfully reproduce the speaking style of the target speaker. In…

Cross-lingual alignment in pretrained language models enables knowledge transfer across languages. Similar alignment has been reported in Whisper-style speech encoders, based on spoken translation retrieval using representational…

Nowadays, as more and more systems achieve good performance in traditional voice conversion (VC) tasks, people's attention gradually turns to VC tasks under extreme conditions. In this paper, we propose a novel method for zero-shot voice…

We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that…

In this paper, we propose a model to perform style transfer of speech to singing voice. Contrary to the previous signal processing-based methods, which require high-quality singing templates or phoneme synchronization, we explore a…

As the recently proposed voice cloning system, NAUTILUS, is capable of cloning unseen voices using untranscribed speech, we investigate the feasibility of using it to develop a unified cross-lingual TTS/VC system. Cross-lingual speech…

With recent advancements in voice cloning, the performance of speech synthesis for a target speaker has been rendered similar to the human level. However, autoregressive voice cloning systems still suffer from text alignment failures,…

The creation of artificial polyglot voices remains a challenging task, despite considerable progress in recent years. This paper investigates self-supervised learning for voice conversion to create native-sounding polyglot voices. We…

Despite rapid progress in text-to-speech (TTS), open-source systems still lack truly instruction-following, fine-grained control over core speech attributes (e.g., pitch, speaking rate, age, emotion, and style). We present VoiceSculptor, an…

A text-to-speech (TTS) model trained to reconstruct speech given text tends towards predictions that are close to the average characteristics of a dataset, failing to model the variations that make human speech sound natural. This problem…

Text-to-speech models trained on large-scale datasets have demonstrated impressive in-context learning capabilities and naturalness. However, control of speaker identity and style in these models typically requires conditioning on reference…

Whistled speech is a little studied local use of language shaped by several cultures of the world either for distant dialogues or for rendering traditional songs. This practice consists of an emulation of the voice thanks to a simple…

Speaker verification is a task of confirming an individual's identity through the analysis of their voice. Whispered speech differs from phonated speech in acoustic characteristics, which degrades the performance of speaker verification…

Non-parallel voice conversion (VC) is typically achieved using lossy representations of the source speech. However, ensuring only speaker identity information is dropped whilst all other information from the source speech is retained is a…

Advancements in AI-synthesized human voices have created a growing threat of impersonation and disinformation, making it crucial to develop methods to detect synthetic human voices. This study proposes a new approach to identifying…

Voice cloning technology poses significant privacy threats by enabling unauthorized speech synthesis from limited audio samples. Existing defenses based on imperceptible adversarial perturbations are vulnerable to common audio preprocessing…

Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for…

This study examines the impact of AI-generated digital clones with self-images on enhancing perceptions and skills in online presentations. A mixed-design experiment with 44 international students compared self-recording videos…

The Multi-speaker Multi-style Voice Cloning Challenge (M2VoC) aims to provide a common sizable dataset as well as a fair testbed for the benchmarking of the popular voice cloning task. Specifically, we formulate the challenge to adapt an…

One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the…