Speaker-Dependent WaveNet Vocoder
نویسندگان
چکیده
In this study, we propose a speaker-dependent WaveNet vocoder, a method of synthesizing speech waveforms with WaveNet, by utilizing acoustic features from existing vocoder as auxiliary features of WaveNet. It is expected that WaveNet can learn a sample-by-sample correspondence between speech waveform and acoustic features. The advantage of the proposed method is that it does not require (1) explicit modeling of excitation signals and (2) various assumptions, which are based on prior knowledge specific to speech. We conducted both subjective and objective evaluation experiments on CMUARCTIC database. From the results of the objective evaluation, it was demonstrated that the proposed method could generate high-quality speech with phase information recovered, which was lost by a mel-cepstrum vocoder. From the results of the subjective evaluation, it was demonstrated that the sound quality of the proposed method was significantly improved from mel-cepstrum vocoder, and the proposed method could capture source excitation information more accurately.
منابع مشابه
Statistical Voice Conversion with WaveNet-Based Waveform Generation
This paper presents a statistical voice conversion (VC) technique with the WaveNet-based waveform generation. VC based on a Gaussian mixture model (GMM) makes it possible to convert the speaker identity of a source speaker into that of a target speaker. However, in the conventional vocoding process, various factors such as F0 extraction errors, parameterization errors and over-smoothing effects...
متن کاملFftnet: a Real-time Speaker-dependent Neural Vocoder
We introduce FFTNet, a deep learning approach synthesizing audio waveforms. Our approach builds on the recent WaveNet project, which showed that it was possible to synthesize a natural sounding audio waveform directly from a deep convolutional neural network. FFTNet offers two improvements over WaveNet. First it is substantially faster, allowing for real-time synthesis of audio waveforms. Secon...
متن کاملNatural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a vocoder to synthesize timedomain waveforms from those spectrograms. Our model achieves a mean opinio...
متن کاملA very low bit rate speech coder using HMM with speaker adaptation
This paper describes a speaker adaptation technique for a phonetic vocoder based on HMM. In the vocoder, the encoder performs phoneme recognition and transmits phoneme indexes and state durations to the decoder, and the decoder synthesizes speech using HMM-based speech synthesis technique. One of the main problems of this vocoder is that the voice characteristics of synthetic speech depend on H...
متن کاملA cross-vocoder study of speaker independent synthetic speech detection using phase information
Current speaker verification systems are vulnerable to advanced speech manipulation techniques such as voice conversion and speaker adaptation for TTS systems. Effective anti-spoofing systems that allow the discrimination between human and synthetic impostors have been developed. However, many of them still present two main drawbacks: speaker dependency and, more importantly, counterfeiting tec...
متن کامل