We propose a novel framework for electrolaryngeal speech intelligibility...
Non-autoregressive (non-AR) sequence-to-seqeunce (seq2seq) models for vo...
Sequence-to-sequence (seq2seq) voice conversion (VC) models have greater...
We propose a new paradigm for maintaining speaker identity in dysarthric...
This paper proposes a novel voice conversion (VC) method based on
non-au...
In this paper, we present an open-source software for developing a
nonpa...
In this paper, we present the voice conversion (VC) systems developed at...
In this paper, a pitch-adaptive waveform generative model named
Quasi-Pe...
In this paper, we integrate a simple non-parallel voice conversion (VC)
...
In this paper, we present a novel technique for a non-parallel voice
con...
In this paper, we investigate the effectiveness of a quasi-periodic Wave...
In this paper, we propose a quasi-periodic neural network (QPNet) vocode...
In this work, we investigate the effectiveness of two techniques for
imp...
This paper presents a refinement framework of WaveNet vocoders for
varia...
In this paper, we propose a technique to alleviate quality degradation c...