paper-with-me

Papers

Fast Spectrogram Inversion using Multi-head Convolutional Neural Networks

2018-08-20 · Sercan O. Arik, Heewoo Jun, Gregory Diamos

We propose the multi-head convolutional neural network (MCNN) architecture for waveform synthesis from spectrograms. Nonlinear interpolation in MCNN is employed with transposed convolution layers in parallel heads. MCNN achieves more than an order of magnitude higher compute intensity than commonly-used iterative algorithms like Griffin-Lim, yielding efficient utilization for modern multi-core processors, and very fast (more than 300x real-time) waveform synthesis. For training of MCNN, we use a large-scale speech recognition dataset and losses defined on waveforms that are related to perceptual audio quality. We demonstrate that MCNN constitutes a very promising approach for high-quality speech synthesis, without any iterative algorithms or autoregression in computations.

📄 PDF Abstract BibTeX arXiv:1808.06719

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech RecognitionSpeech Synthesis

Methods 이 논문이 사용한 방법론

Transposed convolution 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Real time spectrogram inversion on mobile phone

2022-03-01 · Oleg Rybakov, Marco Tagliasacchi, Yunpeng Li, Liyang Jiang 외

We present two methods of real time magnitude spectrogram inversion: streaming Griffin Lim(GL) and streaming MelGAN. We demonstrate the impact of looking ahead on perceptual quality of MelGAN. As little as one hop size (…

CPU

MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

2019-10-08 · NeurIPS 2019 12 · Kundan Kumar, Rithesh Kumar, Thibault de Boissiere, Lucas Gestin 외

Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is possible to train GANs reliably to generate …

CPUGPUSpeech SynthesisTranslation

Mel-Spectrogram Inversion via Alternating Direction Method of Multipliers

2025-01-09 · Yoshiki Masuyama, Natsuki Ueno, Nobutaka Ono

Signal reconstruction from its mel-spectrogram is known as mel-spectrogram inversion and has many applications, including speech and foley sound synthesis. In this paper, we propose a mel-spectrogram inversion method bas…

Frequency-Undersampled Short-Time Fourier Transform

2020-10-28 · Daichi Kitahara

The short-time Fourier transform (STFT) usually computes the same number of frequency components as the frame length while overlapping adjacent time frames by more than half. As a result, the number of components of a sp…

iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform

2022-03-04 · Takuhiro Kaneko, Kou Tanaka, Hirokazu Kameoka, Shogo Seki

In recent text-to-speech synthesis and voice conversion systems, a mel-spectrogram is commonly applied as an intermediate representation, and the necessity for a mel-spectrogram vocoder is increasing. A mel-spectrogram v…

Speech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis+1