paper-with-me

Papers

Real time spectrogram inversion on mobile phone

2022-03-01 · Oleg Rybakov, Marco Tagliasacchi, Yunpeng Li, Liyang Jiang, Xia Zhang, Fadi Biadsy

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 (12.5ms) of lookahead is able to significantly improve perceptual quality in comparison to its causal version. We compare streaming GL with the streaming MelGAN and show different trade-offs in terms of perceptual quality, on-device latency, algorithmic delay, memory footprint and noise sensitivity. For fair quality assessment of the GL approach, we use input log magnitude spectrogram without mel transformation. We evaluate presented real time spectrogram inversion approaches on clean, noisy and atypical speech. We specified conditions when streaming GL has comparable quality with MelGAN: noisy audio and no mel transformation. Streaming GL is 2.4x faster than real time on the ARM CPU of a Pixel4 and it uses 4.5x times less memory than MelGAN.

📄 PDF Abstract BibTeX arXiv:2203.00756

Code (1)

google-research/google-research/tree/master/specinvert 공식 구현 jax

Tasks

CPU

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Dilated Convolution 설명 없음
Residual Connection 설명 없음
Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…
Window-based Discriminator 설명 없음
Weight Normalization Weight Normalization is a normalization method for training neural networks. It is inspired by batch normalization,…
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…
MelGAN Residual Block 설명 없음

Similar Papers 제목 키워드 기반

Music Enhancement via Image Translation and Vocoding

2022-04-28 · Nikhil Kandpal, Oriol Nieto, Zeyu Jin

Consumer-grade music recordings such as those captured by mobile devices typically contain distortions in the form of background noise, reverb, and microphone-induced EQ. This paper presents a deep learning approach to e…

Image-to-Image TranslationTranslation

On-device neural speech synthesis

2021-09-17 · Sivanand Achanta, Albert Antony, Ladan Golipour, Jiangchuan Li 외

Recent advances in text-to-speech (TTS) synthesis, such as Tacotron and WaveRNN, have made it possible to construct a fully neural network based TTS system, by coupling the two components together. Such a system is conce…

GPUSpeech Synthesistext-to-speechText to Speech

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…

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…

Letters hide the truth from our eyes: English homophones have meaningfully different phonetic realizations

2026-08-27 · Yu-Hsiang Tseng, Mirjam T. C. Ernestus, Louis F. M. ten Bosch, R. Harald Baayen arxiv

The distribution of spoken word duration of English homophones is known to co-vary with frequency of use. This study investigates whether other aspects of the phonetic realization of homophones also differ. A series of q…