The NU Voice Conversion System For The Voice Conversion Challenge 2020: On The Effectiveness Of Sequence-to-sequence Models And Autoregressive Neural Vocoders

Abstract

In this paper, we present the voice conversion (VC) systems developed at Nagoya University (NU) for the Voice Conversion Challenge 2020 (VCC2020). We aim to determine the effectiveness of two recent significant technologies in VC: sequence-to-sequence (seq2seq) models and autoregressive (AR) neural vocoders. Two respective systems were developed for the two tasks in the challenge: for task 1, we adopted the Voice Transformer Network, a Transformer-based seq2seq VC model, and extended it with synthetic parallel data to tackle nonparallel data; for task 2, we used the frame-based cyclic variational autoencoder (CycleVAE) to model the spectral features of a speech waveform and the AR WaveNet vocoder with additional fine-tuning. By comparing with the baseline systems, we confirmed that the seq2seq modeling can improve the conversion similarity and that the use of AR vocoders can improve the naturalness of the converted speech.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyhuang2020the

Related papers

• The Neteasegames System For Voice Conversion Challenge 2020 With Vector-quantization Variational Autoencoder And Wavenet (2020)0.00
• Baseline System Of Voice Conversion Challenge 2020 With Cyclic Variational Autoencoder And Parallel Wavegan (2020)4.24
• The Academia Sinica Systems Of Voice Conversion For VCC2020 (2020)3.58
• The Voice Conversion Challenge 2018: Promoting Development Of Parallel And Nonparallel Methods (2018)17.06
• Measuring The Effectiveness Of Voice Conversion On Speaker Identification And Automatic Speech Recognition Systems (2019)0.00
• AAS-VC: On The Generalization Ability Of Automatic Alignment Search Based Non-autoregressive Sequence-to-sequence Voice Conversion (2023)0.00
• Voice Conversion Challenge 2020: Intra-lingual Semi-parallel And Cross-lingual Voice Conversion (2020)12.74
• AC-VC: Non-parallel Low Latency Phonetic Posteriorgrams Based Voice Conversion (2021)7.50