English
Related papers

Related papers: Parallel waveform synthesis based on generative ad…

200 papers

Humans can imagine a scene from a sound. We want machines to do so by using conditional generative adversarial networks (GANs). By applying the techniques including spectral norm, projection discriminator and auxiliary classifier, compared…

Computation and Language · Computer Science 2018-08-14 Chia-Hung Wan , Shun-Po Chuang , Hung-Yi Lee

We introduce a novel method for emotion conversion in speech that does not require parallel training data. Our approach loosely relies on a cycle-GAN schema to minimize the reconstruction error from converting back and forth between emotion…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-12 Ravi Shankar , Jacob Sager , Archana Venkataraman

We investigate the effectiveness of generative adversarial networks (GANs) for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR) systems. Prior work demonstrates that GANs can effectively…

Sound · Computer Science 2018-11-01 Chris Donahue , Bo Li , Rohit Prabhavalkar

Efficient audio synthesis is an inherently difficult machine learning task, as human perception is sensitive to both global structure and fine-scale waveform coherence. Autoregressive models, such as WaveNet, model local structure at the…

The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, because WaveNet relies on…

Separating two sources from an audio mixture is an important task with many applications. It is a challenging problem since only one signal channel is available for analysis. In this paper, we propose a novel framework for singing voice…

Sound · Computer Science 2017-11-15 Zhe-Cheng Fan , Yen-Lin Lai , Jyh-Shing Roger Jang

Popular neural network-based speech enhancement systems operate on the magnitude spectrogram and ignore the phase mismatch between the noisy and clean speech signals. Conditional generative adversarial networks (cGANs) show promise in…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-21 Deepak Baby

Adversarial waveform generation has been a popular approach as the backend of singing voice conversion (SVC) to generate high-quality singing audio. However, the instability of GAN also leads to other problems, such as pitch jitters and U/V…

Sound · Computer Science 2022-01-26 Haohan Guo , Zhiping Zhou , Fanbo Meng , Kai Liu

Audio captioning aims at generating natural language descriptions for audio clips automatically. Existing audio captioning models have shown promising improvement in recent years. However, these models are mostly trained via maximum…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-30 Xinhao Mei , Xubo Liu , Jianyuan Sun , Mark D. Plumbley , Wenwu Wang

Whispered speech is a special way of pronunciation without using vocal cord vibration. A whispered speech does not contain a fundamental frequency, and its energy is about 20dB lower than that of a normal speech. Converting a whispered…

Sound · Computer Science 2021-11-03 Teng Gao , Jian Zhou , Huabin Wang , Liang Tao , Hon Keung Kwan

Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-16 Luka Chkhetiani , Levan Bejanidze

Entertainment-oriented singing voice synthesis (SVS) requires a vocoder to generate high-fidelity (e.g. 48kHz) audio. However, most text-to-speech (TTS) vocoders cannot reconstruct the waveform well in this scenario. In this paper, we…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-19 Chunhui Wang , Chang Zeng , Jun Chen , Xing He

Recent studies have shown that text-to-speech synthesis quality can be improved by using glottal vocoding. This refers to vocoders that parameterize speech into two parts, the glottal excitation and vocal tract, that occur in the human…

Audio and Speech Processing · Electrical Eng. & Systems 2019-03-15 Bajibabu Bollepalli , Lauri Juvela , Paavo Alku

This paper proposes a spectral-domain perceptual weighting technique for Parallel WaveGAN-based text-to-speech (TTS) systems. The recently proposed Parallel WaveGAN vocoder successfully generates waveform sequences using a fast…

Audio and Speech Processing · Electrical Eng. & Systems 2021-01-20 Eunwoo Song , Ryuichi Yamamoto , Min-Jae Hwang , Jin-Seob Kim , Ohsung Kwon , Jae-Min Kim

Conditional waveform synthesis models learn a distribution of audio waveforms given conditioning such as text, mel-spectrograms, or MIDI. These systems employ deep generative models that model the waveform via either sequential…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-07 Max Morrison , Rithesh Kumar , Kundan Kumar , Prem Seetharaman , Aaron Courville , Yoshua Bengio

This paper introduces WaveNet, a deep neural network for generating raw audio waveforms. The model is fully probabilistic and autoregressive, with the predictive distribution for each audio sample conditioned on all previous ones;…

We propose the HumanGAN, a generative adversarial network (GAN) incorporating human perception as a discriminator. A basic GAN trains a generator to represent a real-data distribution by fooling the discriminator that distinguishes real and…

Sound · Computer Science 2019-09-26 Kazuki Fujii , Yuki Saito , Shinnosuke Takamichi , Yukino Baba , Hiroshi Saruwatari

Speech synthesis is used in a wide variety of industries. Nonetheless, it always sounds flat or robotic. The state of the art methods that allow for prosody control are very cumbersome to use and do not allow easy tuning. To tackle some of…

Sound · Computer Science 2021-10-08 Enrique Hortal , Rodrigo Brechard Alarcia

Autoregressive neural vocoders have achieved outstanding performance in speech synthesis tasks such as text-to-speech and voice conversion. An autoregressive vocoder predicts a sample at some time step conditioned on those at previous time…

Sound · Computer Science 2024-06-06 Po-chun Hsu , Da-rong Liu , Andy T. Liu , Hung-yi Lee

Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources. We propose a novel generative model based on cyclic-consistent generative adversarial network (CycleGAN) for…

Computation and Language · Computer Science 2018-07-11 Ehsan Hosseini-Asl , Yingbo Zhou , Caiming Xiong , Richard Socher