DuraMark: Duration-Embedded Watermarking in LLM-based TTS

Large language model (LLM)-based text-to-speech (TTS) models have achieved remarkable voice cloning capabilities, raising concerns about potential deepfake misuse. Speech watermarking mitigates this by embedding traceable information into generated speech. Mainstream watermarking methods operate at the signal level (waveform or spectrogram), rendering the watermark vulnerable to generative attacks (e.g., neural codec and vocoder). To address this, we propose DuraMark, a robust information-level watermarking framework. It utilizes syllable duration editing to achieve watermark embedding. Specifically, DuraMark integrates a duration-controllable LLM-based TTS model to edit syllable durations during synthesis, coupled with a duration extractor to extract these durations for detection. Experiments demonstrate DuraMark's superior robustness against generative attacks, significantly outperforming signal-level baselines. Audio samples are available at https://muzw.github.io/duramark_demo/.

Visual Place Recognition

Visual position recognition affects the safety and accuracy of automatic driving. To accurately identify the location, this paper studies a visual place recognition algorithm based on HMM filter and HMM smoother. Firstly, we constructed the traffic situations in Canberra city. Then the mathematical models of the HMM filter and HMM smoother were performed. Finally, the vehicle position was predicted based on the algorithms. Experiment results show that HMM smoother is better than HMM filter in terms of prediction accuracy.