Reverberation Modeling for Source-Filter-based Neural Vocoder

Ai, Yang; Wang, Xin; Yamagishi, Junichi; Ling, Zhen-Hua

doi:10.48550/arxiv.2005.07379

Cited by 2 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is because our neural vocoder was pretrained only with high-quality but dry waveforms. We plan to alleviate this issue by using a recently proposed reverberationaware vocoder [32], which is able to model reverberation and generate a reverberant waveform with high perceived quality.…”

Section: Discussionmentioning

confidence: 99%

Enhancing Low-Quality Voice Recordings Using Disentangled Channel Factor and Neural Waveform Model

Yamagishi

2021

2021 IEEE Spoken Language Technology Workshop (SLT)

Self Cite

View full text Add to dashboard Cite

High-quality speech corpora are essential foundations for most speech applications. However, such speech data are expensive and limited since they are collected in professional recording environments. In this work, we propose an encoder-decoder neural network to automatically enhance low-quality recordings to professional high-quality recordings. To address channel variability, we first filter out the channel characteristics from the original input audio using the encoder network with adversarial training. Next, we disentangle the channel factor from a reference audio. Conditioned on this factor, an auto-regressive decoder is then used to predict the target-environment Mel spectrogram. Finally, we apply a neural vocoder to synthesize the speech waveform. Experimental results show that the proposed system can generate a professional high-quality speech waveform when setting high-quality audio as the reference. It also improves speech enhancement performance compared with several state-of-the-art baseline systems.

show abstract

Section: Discussionmentioning

confidence: 99%