Parallel waveform synthesis based on generative adversarial networks with voicing-aware conditional discriminators
This paper proposes voicing-aware conditional discriminators for Parallel WaveGAN-based waveform synthesis systems. In this framework, we adopt a projection-based conditioning method that can significantly improve the discriminator's performance. Furthermore, the conventional discriminator is separated into two waveform discriminators for modeling voiced and unvoiced speech. As each discriminator learns the distinctive characteristics of the harmonic and noise components, respectively, the adversarial training process becomes more efficient, allowing the generator to produce more realistic speech waveforms. Subjective test results demonstrate the superiority of the proposed method over the conventional Parallel WaveGAN and WaveNet systems. In particular, our speaker-independently trained model within a FastSpeech 2 based text-to-speech framework achieves the mean opinion scores of 4.20, 4.18, 4.21, and 4.31 for four Japanese speakers, respectively.
Code (0)
등록된 구현이 없습니다.
Tasks
text-to-speechText to SpeechMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Speech waveform synthesis from MFCC sequences with generative adversarial networks
This paper proposes a method for generating speech from filterbank mel frequency cepstral coefficients (MFCC), which are widely used in speech applications, such as ASR, but are generally considered unusable for speech s…
Generative Adversarial NetworkSpeech SynthesisWaveform generation for text-to-speech synthesis using pitch-synchronous multi-scale generative adversarial networks
The state-of-the-art in text-to-speech synthesis has recently improved considerably due to novel neural waveform generation methods, such as WaveNet. However, these methods suffer from their slow sequential inference pro…
Image GenerationSpeech Synthesistext-to-speechText to Speech+2An Initial study on Birdsong Re-synthesis Using Neural Vocoders
Modern speech synthesis uses neural vocoders to model raw waveform samples directly. This increased versatility has expanded the scope of vocoders from speech to other domains, such as music. We address another interesti…
ResynthesisSpeech SynthesisTFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis
Recently, GAN based speech synthesis methods, such as MelGAN, have become very popular. Compared to conventional autoregressive based methods, parallel structures based generators make waveform generation process fast an…
Generative Adversarial NetworkSpeech SynthesisChunked Autoregressive GAN for Conditional Waveform Synthesis
Conditional waveform synthesis models learn a distribution of audio waveforms given conditioning such as text, mel-spectrograms, or MIDI. These systems employ deep generative models that model the waveform via either seq…
Inductive Bias