mlsanityData to 13 Oct 2026

Automatic Voice Identification after Speech Resynthesis using PPG

arXiv 2408.02712 ↗First posted 5 Aug 2024cs.SD cs.AI cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

Speech resynthesis is a generic task for which we want to synthesize audio with another audio as input, which finds applications for media monitors and journalists.Among different tasks addressed by speech resynthesis, voice conversion preserves the linguistic information while modifying the identity of the speaker, and speech edition preserves the identity of the speaker but some words are modified.In both cases, we need to disentangle speaker and phonetic contents in intermediate representations.Phonetic PosteriorGrams (PPG) are a frame-level probabilistic representation of phonemes, and are usually considered speaker-independent.This paper presents a PPG-based speech resynthesis system.A perceptive evaluation assesses that it produces correct audio quality.Then, we demonstrate that an automatic speaker verification model is not able to recover the source speaker after re-synthesis with PPG, even when the model is trained on synthetic data.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 19 of its 26 references that are in the map. First posted on arXiv 5 Aug 2024.

Builds on

19 of 26 references.

References · 19

  1. 2016WaveNet: A Generative Model for Raw Audiocited by 1,717
  2. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,625
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,148
  4. 2018VoxCeleb2: Deep Speaker Recognitioncited by 864
  5. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 803
  6. 2017VoxCeleb: a large-scale speaker identification datasetcited by 719
  7. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 643
  8. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 612
  9. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 559
  10. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 309
  11. 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 151
  12. 2020Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversioncited by 75
7 more
  1. 2019BUT System Description to VoxCeleb Speaker Recognition Challenge 2019cited by 51
  2. 2019Speaker Anonymization Using X-vector and Neural Waveform Modelscited by 41
  3. 2021EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusioncited by 31
  4. 2021EdiTTS: Score-based Editing for Controllable Text-to-Speechcited by 28
  5. 2023The Singing Voice Conversion Challenge 2023cited by 25
  6. 2018Rhythm-Flexible Voice Conversion without Parallel Data Using Cycle-GAN over Phoneme Posteriorgram Sequencescited by 4
  7. 2019Taco-VC: A Single Speaker Tacotron based Voice Conversion with Limited Datacited by 1

Built on by

Not cited yet.