2022/09/24 by Jixun Yao, Qing Wang, Yao, Jixun +9 · 5 citations
Computer Science · Engineering · #Artificial intelligence #Audio and Speech Processing (eess.AS) #Computer science #Data mining #Embedding #Encoder #Engineering #Extractor #FOS: Computer and information sciences #FOS: Electrical engineering #Feature (linguistics) #Natural Language Processing Techniques #Pattern recognition (psychology) #SIGNAL (programming language) #Sound (cs.SD) #Speaker diarisation #Speaker recognition #Speaker verification #Spectrogram #Speech Recognition and Synthesis #Speech and Audio Processing #Speech recognition #Table (database) #Telecommunications #Waveform #cs.SD #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2209.11969
published in arXiv (Cornell University) (Cornell University) · VoicePrivacy 2022 Challenge
arxiv created 2022/09/24 · openalex publication_date 2022/09/24 · arxiv updated 2022/09/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
This paper presents the NWPU-ASLP speaker anonymization system for VoicePrivacy 2022 Challenge. Our submission does not involve additional Automatic Speaker Verification (ASV) model or x-vector pool. Our system consists of four modules, including feature extractor, acoustic model, anonymization module, and neural vocoder. First, the feature extractor extracts the Phonetic Posteriorgram (PPG) and pitch from the input speech signal. Then, we reserve a pseudo speaker ID from a speaker look-up table (LUT), which is subsequently fed into a speaker encoder to generate the pseudo speaker embedding that is not corresponding to any real speaker. To ensure the pseudo speaker is distinguishable, we further average the randomly selected speaker embedding and weighted concatenate it with the pseudo speaker embedding to generate the anonymized speaker embedding. Finally, the acoustic model outputs the anonymized mel-spectrogram from the anonymized speaker embedding and a modified version of HifiGAN transforms the mel-spectrogram into the anonymized speech waveform. Experimental results demonstrate the effectiveness of our proposed anonymization system.