paper-with-me

Papers

Parallel waveform synthesis based on generative adversarial networks with voicing-aware conditional discriminators

2020-10-27 · Ryuichi Yamamoto, Eunwoo Song, Min-Jae Hwang, Jae-Min Kim

This paper proposes voicing-aware conditional discriminators for Parallel WaveGAN-based waveform synthesis systems. In this framework, we adopt a projection-based conditioning method that can significantly improve the discriminator's performance. Furthermore, the conventional discriminator is separated into two waveform discriminators for modeling voiced and unvoiced speech. As each discriminator learns the distinctive characteristics of the harmonic and noise components, respectively, the adversarial training process becomes more efficient, allowing the generator to produce more realistic speech waveforms. Subjective test results demonstrate the superiority of the proposed method over the conventional Parallel WaveGAN and WaveNet systems. In particular, our speaker-independently trained model within a FastSpeech 2 based text-to-speech framework achieves the mean opinion scores of 4.20, 4.18, 4.21, and 4.31 for four Japanese speakers, respectively.

📄 PDF Abstract BibTeX arXiv:2010.14151

Code (0)

등록된 구현이 없습니다.

Tasks

text-to-speechText to Speech

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
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 $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
FastSpeech 2 FastSpeech2 is a text-to-speech model that aims to improve upon FastSpeech by better solving the one-to-many mapping problem in TTS, i.e., multiple speech variations…

Similar Papers 제목 키워드 기반

Speech waveform synthesis from MFCC sequences with generative adversarial networks

2018-04-03 · Lauri Juvela, Bajibabu Bollepalli, Xin Wang, Hirokazu Kameoka 외

This paper proposes a method for generating speech from filterbank mel frequency cepstral coefficients (MFCC), which are widely used in speech applications, such as ASR, but are generally considered unusable for speech s…

Generative Adversarial NetworkSpeech Synthesis

Waveform generation for text-to-speech synthesis using pitch-synchronous multi-scale generative adversarial networks

2018-10-30 · Lauri Juvela, Bajibabu Bollepalli, Junichi Yamagishi, Paavo Alku

The state-of-the-art in text-to-speech synthesis has recently improved considerably due to novel neural waveform generation methods, such as WaveNet. However, these methods suffer from their slow sequential inference pro…

Image GenerationSpeech Synthesistext-to-speechText to Speech+2

An Initial study on Birdsong Re-synthesis Using Neural Vocoders

2022-09-21 · Rhythm Bhatia, Tomi H. Kinnunen

Modern speech synthesis uses neural vocoders to model raw waveform samples directly. This increased versatility has expanded the scope of vocoders from speech to other domains, such as music. We address another interesti…

ResynthesisSpeech Synthesis

TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis

2020-11-24 · Qiao Tian, Yi Chen, Zewang Zhang, Heng Lu 외

Recently, GAN based speech synthesis methods, such as MelGAN, have become very popular. Compared to conventional autoregressive based methods, parallel structures based generators make waveform generation process fast an…

Generative Adversarial NetworkSpeech Synthesis

Chunked Autoregressive GAN for Conditional Waveform Synthesis

2021-10-19 · ICLR 2022 4 · Max Morrison, Rithesh Kumar, Kundan Kumar, Prem Seetharaman 외

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 seq…

Inductive Bias