English
Related papers

Related papers: iSTFTNet2: Faster and More Lightweight iSTFT-Based…

200 papers

Recent advancements in speech synthesis have leveraged GAN-based networks like HiFi-GAN and BigVGAN to produce high-fidelity waveforms from mel-spectrograms. However, these networks are computationally expensive and parameter-heavy.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-19 Yinghao Aaron Li , Cong Han , Xilin Jiang , Nima Mesgarani

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 vocoder must solve…

Sound · Computer Science 2022-03-07 Takuhiro Kaneko , Kou Tanaka , Hirokazu Kameoka , Shogo Seki

This paper presents FastFit, a novel neural vocoder architecture that replaces the U-Net encoder with multiple short-time Fourier transforms (STFTs) to achieve faster generation rates without sacrificing sample quality. We replaced each…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-19 Won Jang , Dan Lim , Heayoung Park

Deep learning based speech enhancement in the short-time Fourier transform (STFT) domain typically uses a large window length such as 32 ms. A larger window can lead to higher frequency resolution and potentially better enhancement. This…

Sound · Computer Science 2022-12-07 Zhong-Qiu Wang , Gordon Wichern , Shinji Watanabe , Jonathan Le Roux

Conventional 3D convolutional neural networks (CNNs) are computationally expensive, memory intensive, prone to overfitting, and most importantly, there is a need to improve their feature learning capabilities. To address these issues, we…

Computer Vision and Pattern Recognition · Computer Science 2021-05-05 Sudhakar Kumawat , Manisha Verma , Yuta Nakashima , Shanmuganathan Raman

Transformer has shown promise in reinforcement learning to model time-varying features for obtaining generalized low-level robot policies on diverse robotics datasets in embodied learning. However, it still suffers from the issues of low…

Machine Learning · Computer Science 2024-12-19 Hengkai Tan , Songming Liu , Kai Ma , Chengyang Ying , Xingxing Zhang , Hang Su , Jun Zhu

This work proposes a multichannel narrow-band speech separation network. In the short-time Fourier transform (STFT) domain, the proposed network processes each frequency independently, and all frequencies use a shared network. For each…

Sound · Computer Science 2022-12-06 Changsheng Quan , Xiaofei Li

In our previous work, we proposed a neural vocoder called APNet, which directly predicts speech amplitude and phase spectra with a 5 ms frame shift in parallel from the input acoustic features, and then reconstructs the 16 kHz speech…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-21 Hui-Peng Du , Ye-Xin Lu , Yang Ai , Zhen-Hua Ling

Training deep neural networks (DNNs) requires significantly more computation and memory than inference, making runtime adaptation of DNNs challenging on resource-limited IoT platforms. We propose InstantFT, an FPGA-based method for…

Machine Learning · Computer Science 2025-06-10 Keisuke Sugiura , Hiroki Matsutani

This paper proposes a novel bidirectional neural vocoder, named BiVocoder, capable both of feature extraction and reverse waveform generation within the short-time Fourier transform (STFT) domain. For feature extraction, the BiVocoder takes…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-05 Hui-Peng Du , Ye-Xin Lu , Yang Ai , Zhen-Hua Ling

Recent successful applications of convolutional neural networks (CNNs) to audio classification and speech recognition have motivated the search for better input representations for more efficient training. Visual displays of an audio…

Computer Vision and Pattern Recognition · Computer Science 2017-06-23 M. Huzaifah

Two-stage pipeline is popular in speech enhancement tasks due to its superiority over traditional single-stage methods. The current two-stage approaches usually enhance the magnitude spectrum in the first stage, and further modify the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-22 Yuewei Zhang , Huanbin Zou , Jie Zhu

In this paper, we introduce a spectral-domain inverse filtering approach for single-channel speech de-reverberation using deep convolutional neural network (CNN). The main goal is to better handle realistic reverberant conditions where the…

Sound · Computer Science 2020-10-16 Hanwook Chung , Vikrant Singh Tomar , Benoit Champagne

Recently, deep neural networks (DNNs) have been successfully used for speech enhancement, and DNN-based speech enhancement is becoming an attractive research area. While time-frequency masking based on the short-time Fourier transform…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-21 Yuichiro Koyama , Tyler Vuong , Stefan Uhlich , Bhiksha Raj

Many neural speech enhancement and source separation systems operate in the time-frequency domain. Such models often benefit from making their Short-Time Fourier Transform (STFT) front-ends trainable. In current literature, these are…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-24 Jonah Casebeer , Umut Isik , Shrikant Venkataramani , Arvindh Krishnaswamy

Structured CNN designed using the prior information of problems potentially improves efficiency over conventional CNNs in various tasks in solving PDEs and inverse problems in signal processing. This paper introduces BNet2, a simplified…

Machine Learning · Computer Science 2020-05-21 Zhongshu Xu , Yingzhou Li , Xiuyuan Cheng

In this paper, we address the problem of multichannel speech enhancement in the short-time Fourier transform (STFT) domain. A long short-time memory (LSTM) network takes as input a sequence of STFT coefficients associated with a frequency…

Sound · Computer Science 2020-09-24 Xiaofei LI , Radu Horaud

This work proposes a multichannel speech separation method with narrow-band Conformer (named NBC). The network is trained to learn to automatically exploit narrow-band speech separation information, such as spatial vector clustering of…

Sound · Computer Science 2022-07-04 Changsheng Quan , Xiaofei Li

This paper proposes a new loss using short-time Fourier transform (STFT) spectra for the aim of training a high-performance neural speech waveform model that predicts raw continuous speech waveform samples directly. Not only amplitude…

Audio and Speech Processing · Electrical Eng. & Systems 2018-10-31 Shinji Takaki , Toru Nakashika , Xin Wang , Junichi Yamagishi

Over the past few years, speech enhancement methods based on deep learning have greatly surpassed traditional methods based on spectral subtraction and spectral estimation. Many of these new techniques operate directly in the the short-time…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-28 Jean-Marc Valin , Umut Isik , Neerad Phansalkar , Ritwik Giri , Karim Helwani , Arvindh Krishnaswamy
‹ Prev 1 2 3 10 Next ›