IEEE/ACM Transactions on Audio Speech and Language Processing · 2024 · 20 citations · 32 references
Language StudiesLinguisticsComputational LinguisticsNatural Language ProcessingPhoneticsGenerative ModelingNatural Language GenerationProsody ProcessingSpeech ProductionSpeech RecognitionSpeech SynthesisAutoregressive ModelsAutoregressive ProcessesGenerative Adversarial NetworksProsody AnalysisProsody ModelingProsody PredictionText-to-speech Synthesis
Expressive text-to-speech systems have undergone significant advancements owing to prosody modeling, but conventional methods can still be improved. Traditional approaches have relied on the autoregressive method to predict the quantized prosody vector; however, it suffers from the issues of long-term dependency and slow inference. This study proposes a novel approach called DiffProsody in which expressive speech is synthesized using a diffusion-based latent prosody generator and prosody conditional adversarial training. Our findings confirm the effectiveness of our prosody generator in generating a prosody vector. Furthermore, our prosody conditional discriminator significantly improves the quality of the generated speech by accurately emulating prosody. We use denoising diffusion generative adversarial networks to improve the prosody generation speed. Consequently, DiffProsody is capable of generating prosody 16 times faster than the conventional diffusion model. The superior performance of our proposed method has been demonstrated via experiments.
32
Image quality assessment: from error visibility to structural similarity
Zhou Wang, Alan C. Bovik, Hamid R. Sheikh et al. · IEEE Transactions on Image Processing · 2004 · 56K citations
Least Squares Generative Adversarial Networks
Xudong Mao, Qing Li, Haoran Xie et al. · 2017 · 5.2K citations
Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions
Jonathan Shen, Ruoming Pang, Ron J. Weiss et al. · 2018 · 2.7K citations