Voice conversion in high-order eigen space using deep belief nets

By Toru Nakashika, R. Takashima, Tetsuya Takiguchi, Yasuo Ariki. 2013

142 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Junichi Yamagishi
2. Haizhou Li
3. Xin Eric Wang
4. Zhenhua Ling
5. Li Deng
6. Dong Yu
7. Tao Qin
8. Xu Tan

In Signal Processing

1. Junichi Yamagishi
2. Haizhou Li
3. Li Deng
4. Zhenhua Ling
5. Dong Yu
6. Xin Eric Wang
7. Yu Tsao
8. Tomoki Toda

Citations in the corpus

• Deep Learning: Methods and Applications (2014, background): “to emotion recognition from speech in [207, 222], to spoken language understanding in [242, 366, 403], to speaker recognition in [351, 372], to language-type recognition in [112], to dialogue state tracking for spoken dialogue systems in [94, 152], to automatic voice activity detection in [442], to ”
• Joint training framework for text-to-speech and voice conversion using multi-source Tacotron and WaveNet (2019, background): “Dynamic kernel partial least squares regression (DKPLS) [7] and neural network based approaches [8, 9, 10, 11, 12] learn non-linear transforms.”
• Emotional voice conversion using deep neural networks with MCC and F0 features (2016, methodology): “Since the deep brief networks are effective to spectral envelopes converting [13], in the proposed model, we train the MCC features by using two DBNs for the source speaker and the target speaker, respectively, then using the NNs to connect the two DBNs for converting the individuality abstractions ”
• Spoofing and countermeasures for speaker verification: A survey (2015, background): “, 2013) and deep belief networks (Nakashika et al., 2013).”
• Voice Morphing that improves TTS quality using an optimal dynamic frequency warping-and-weighting transform (2016, background): “Neural-Network-based speech synthesis [11, 12] can also benefit from adaptation [13, 14].”
• Locally Linear Embedding for Exemplar-Based Spectral Conversion (2016, methodology): “Numerous VC approaches have been proposed, such as Gaussian mixture model (GMM)-based [1-4], frequency warpingbased [5, 6], neural networks (NN)-based [7-10], and exemplar-based [11-13] approaches.”
• A probabilistic interpretation for artificial neural network-based voice conversion (2015, methodology): “Numerous VC approaches [1-12] have been proposed based on various models.”
• Voice Conversion Using Deep Neural Networks With Layer-Wise Generative Training (2014, methodology): “…by using trajectory-level in­formation, e.g., integrating dynamic features and global vari­ance (GV) into the conventional parameter generation criterion [11], reformulating the frame-level GMM as a trajectory model for modeling and generating sentence-level feature trajectories [12], etc.”
• Phonetic posteriorgrams for many-to-one voice conversion without parallel data training (2016, methodology): “[4] used a Deep Neural Network (DNN) to map the source and target in high order space.”
• Postfilters to Modify the Modulation Spectrum for Statistical Parametric Speech Synthesis (2016, methodology): “Nowadays, many technologies have been studied within this basic framework, including speech synthesis using Hidden Markov Models (HMM) [13], Gaussian Mixture Model (GMM) [14], Classification And Regression Trees (CART) [15], kernel regression [16], [17], and Deep Neural Nets (DNN) [18], [19].”