Speaker Independence Of Neural Vocoders And Their Effect On Parametric Resynthesis Speech Enhancement

Abstract

Traditional speech enhancement systems produce speech with compromised quality. Here we propose to use the high quality speech generation capability of neural vocoders for better quality speech enhancement. We term this parametric resynthesis (PR). In previous work, we showed that PR systems generate high quality speech for a single speaker using two neural vocoders, WaveNet and WaveGlow. Both these vocoders are traditionally speaker dependent. Here we first show that when trained on data from enough speakers, these vocoders can generate speech from unseen speakers, both male and female, with similar quality as seen speakers in training. Next using these two vocoders and a new vocoder LPCNet, we evaluate the noise reduction quality of PR on unseen speakers and show that objective signal and overall quality is higher than the state-of-the-art speech enhancement systems Wave-U-Net, Wavenet-denoise, and SEGAN. Moreover, in subjective quality, multiple-speaker PR out-performs the oracle Wi

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keymaiti2019speaker

Related papers

• Speech Denoising By Parametric Resynthesis (2019)7.16
• Parametric Resynthesis With Neural Vocoders (2019)8.60
• Speaker-adaptive Neural Vocoders For Parametric Speech Synthesis Systems (2018)2.26
• Evaluation Of The Speech Resynthesis Capabilities Of The Voiceprivacy Challenge Baseline B1 (2023)3.58
• A Comparison Of Recent Waveform Generation And Acoustic Modeling Methods For Neural-network-based Speech Synthesis (2018)11.76
• Towards Robust Neural Vocoding For Speech Generation: A Survey (2019)0.00
• La-voce: Low-snr Audio-visual Speech Enhancement Using Neural Vocoders (2022)0.00
• Towards Parametric Speech Synthesis Using Gaussian-markov Model Of Spectral Envelope And Wavelet-based Decomposition Of F0 (2022)0.00