Collapsed Speech Segment Detection And Suppression For Wavenet Vocoder

Abstract

In this paper, we propose a technique to alleviate the quality degradation caused by collapsed speech segments sometimes generated by the WaveNet vocoder. The effectiveness of the WaveNet vocoder for generating natural speech from acoustic features has been proved in recent works. However, it sometimes generates very noisy speech with collapsed speech segments when only a limited amount of training data is available or significant acoustic mismatches exist between the training and testing data. Such a limitation on the corpus and limited ability of the model can easily occur in some speech generation applications, such as voice conversion and speech enhancement. To address this problem, we propose a technique to automatically detect collapsed speech segments. Moreover, to refine the detected segments, we also propose a waveform generation technique for WaveNet using a linear predictive coding constraint. Verification and subjective tests are conducted to investigate the effectiveness o

Stats

• citations15
• S2 citations—
• github stars0
• HF likes0
• heat score9.03
• arxiv keywu2018collapsed

Related papers

• Non-parallel Voice Conversion System With Wavenet Vocoder And Collapsed Speech Suppression (2020)3.58
• Refined Wavenet Vocoder For Variational Autoencoder Based Voice Conversion (2018)7.50
• Empirical Evaluation Of Deep Learning Model Compression Techniques On The Wavenet Vocoder (2020)0.00
• A Vocoder-free Wavenet Voice Conversion With Non-parallel Data (2019)0.00
• A Neural Denoising Vocoder For Clean Waveform Generation From Noisy Mel-spectrogram Based On Amplitude And Phase Predictions (2024)0.00
• A Wavenet For Speech Denoising (2017)18.47
• Lp-wavenet: Linear Prediction-based Wavenet Speech Synthesis (2018)0.00
• Wasserstein GAN And Waveform Loss-based Acoustic Model Training For Multi-speaker Text-to-speech Synthesis Systems Using A Wavenet Vocoder (2018)12.61