paper-with-me

Papers

Neural source-filter waveform models for statistical parametric speech synthesis

2019-04-27 · Xin Wang, Shinji Takaki, Junichi Yamagishi

Neural waveform models such as WaveNet have demonstrated better performance than conventional vocoders for statistical parametric speech synthesis. As an autoregressive (AR) model, WaveNet is limited by a slow sequential waveform generation process. Some new models that use the inverse-autoregressive flow (IAF) can generate a whole waveform in a one-shot manner. However, these IAF-based models require sequential transformation during training, which severely slows down the training speed. Other models such as Parallel WaveNet and ClariNet bring together the benefits of AR and IAF-based models and train an IAF model by transferring the knowledge from a pre-trained AR teacher to an IAF student without any sequential transformation. However, both models require additional training criteria, and their implementation is prohibitively complicated. We propose a framework for neural source-filter (NSF) waveform modeling without AR nor IAF-based approaches. This framework requires only three components for waveform generation: a source module that generates a sine-based signal as excitation, a non-AR dilated-convolution-based filter module that transforms the excitation into a waveform, and a conditional module that pre-processes the acoustic features for the source and filer modules. This framework minimizes spectral-amplitude distances for model training, which can be efficiently implemented by using short-time Fourier transform routines. Under this framework, we designed three NSF models and compared them with WaveNet. It was demonstrated that the NSF models generated waveforms at least 100 times faster than WaveNet, and the quality of the synthetic speech from the best NSF model was better than or equally good as that from WaveNet.

📄 PDF Abstract BibTeX arXiv:1904.12088

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Synthesis

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Weight Normalization Weight Normalization is a normalization method for training neural networks. It is inspired by batch normalization,…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
L1 Regularization $L_{1}$ Regularization is a regularization technique applied to the weights of a neural network. We minimize a loss function compromising both the primary loss function and a…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softsign Activation Softsign is an activation function for neural networks: $$ f\left(x\right) = \left(\frac{x}{|x|+1}\right)$$ Image Source: [Sefik Ilkin…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Neural source-filter-based waveform model for statistical parametric speech synthesis

2018-10-29 · Xin Wang, Shinji Takaki, Junichi Yamagishi

Neural waveform models such as the WaveNet are used in many recent text-to-speech systems, but the original WaveNet is quite slow in waveform generation because of its autoregressive (AR) structure. Although faster non-A…

Speech Synthesistext-to-speechText to Speech

WaveCycleGAN2: Time-domain Neural Post-filter for Speech Waveform Generation

2019-04-05 · Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Nobukatsu Hojo

WaveCycleGAN has recently been proposed to bridge the gap between natural and synthesized speech waveforms in statistical parametric speech synthesis and provides fast inference with a moving average model rather than an…

Speech Synthesis

A Waveform Representation Framework for High-quality Statistical Parametric Speech Synthesis

2015-10-06 · Bo Fan, Siu Wa Lee, Xiaohai Tian, Lei Xie 외

State-of-the-art statistical parametric speech synthesis (SPSS) generally uses a vocoder to represent speech signals and parameterize them into features for subsequent modeling. Magnitude spectrum has been a dominant fea…

Speech SynthesisVocal Bursts Intensity Prediction

Continuous Wavelet Vocoder-based Decomposition of Parametric Speech Waveform Synthesis

2021-06-12 · Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Csaba Zainkó, Géza Németh

To date, various speech technology systems have adopted the vocoder approach, a method for synthesizing speech waveform that shows a major role in the performance of statistical parametric speech synthesis. WaveNet one o…

Speech Synthesis

WaveCycleGAN: Synthetic-to-natural speech waveform conversion using cycle-consistent adversarial networks

2018-09-25 · Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo, Hirokazu Kameoka

We propose a learning-based filter that allows us to directly modify a synthetic speech waveform into a natural speech waveform. Speech-processing systems using a vocoder framework such as statistical parametric speech s…

Speech SynthesisVoice Conversion