Related papers: TraceableSpeech: Towards Proactively Traceable Tex…

Watermarking technology is a method used to trace the usage of content generated by large language models. Sentence-level watermarking aids in preserving the semantic integrity within individual sentences while maintaining greater…

The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a promising solution: model owners can embed an imperceptible…

As large language models become increasingly capable and widely deployed, verifying the provenance of machine-generated content is critical to ensuring trust, safety, and accountability. Watermarking techniques have emerged as a promising…

The recent progress in non-autoregressive text-to-speech (NAR-TTS) has made fast and high-quality speech synthesis possible. However, current NAR-TTS models usually use phoneme sequence as input and thus cannot understand the…

With the advancement of speech synthesis technology, users have higher expectations for the naturalness and expressiveness of synthesized speech. But previous research ignores the importance of prompt selection. This study proposes a…

Several recently proposed text-to-speech (TTS) models achieved to generate the speech samples with the human-level quality in the single-speaker and multi-speaker TTS scenarios with a set of pre-defined speakers. However, synthesizing a new…

Watermarking is a promising defense against the misuse of large language models (LLMs), yet it remains vulnerable to scrubbing and spoofing attacks. This vulnerability stems from an inherent trade-off governed by watermark window size:…

Some recent studies have demonstrated the feasibility of single-stage neural text-to-speech, which does not need to generate mel-spectrograms but generates the raw waveforms directly from the text. Single-stage text-to-speech often faces…

Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into…

In recent years, Text-To-Speech (TTS) has been used as a data augmentation technique for speech recognition to help complement inadequacies in the training data. Correspondingly, we investigate the use of a multi-speaker TTS system to…

The rise of LLMs has increased concerns over source tracing and copyright protection for AIGC, highlighting the need for advanced detection technologies. Passive detection methods usually face high false positives, while active watermarking…

Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data…

Attention-based end-to-end text-to-speech synthesis (TTS) is superior to conventional statistical methods in many ways. Transformer-based TTS is one of such successful implementations. While Transformer TTS models the speech frame sequence…

Watermarking embeds information into digital content like images, audio, or text, imperceptible to humans but robustly detectable by specific algorithms. This technology has important applications in many challenges of the industry such as…

We present a neural text-to-speech (TTS) method that models natural vocal effort variation to improve the intelligibility of synthetic speech in the presence of noise. The method consists of first measuring the spectral tilt of unlabeled…

Previous works on neural text-to-speech (TTS) have been addressed on limited speed in training and inference time, robustness for difficult synthesis conditions, expressiveness, and controllability. Although several approaches resolve some…

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…

Generating speech across different accents while preserving speaker identity is crucial for various real-world applications. However, accurately and independently modeling both speaker and accent characteristics in text-to-speech (TTS)…

Text watermarking schemes have gained considerable attention in recent years, yet still face critical challenges in achieving simultaneous robustness, generalizability, and imperceptibility. This paper introduces a new embedding…

Recently, sequence-to-sequence (seq-to-seq) models have been successfully applied in text-to-speech (TTS) to synthesize speech for single-language text. To synthesize speech for multiple languages usually requires multi-lingual speech from…