English
Related papers

Related papers: A Speech Enhancement Method Using Fast Fourier Tra…

200 papers

Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…

Sound · Computer Science 2023-10-18 Christian J. Steinmetz , Thomas Walther , Joshua D. Reiss

This paper aims to develop a new and robust approach to feature representation. Motivated by the success of Auto-Encoders, we first theoretical summarize the general properties of all algorithms that are based on traditional Auto-Encoders:…

Machine Learning · Computer Science 2018-10-24 Zeng Yu , Tianrui Li , Ning Yu , Yi Pan , Hongmei Chen , Bing Liu

Pre-trained speech Transformers have facilitated great success across various speech processing tasks. However, fine-tuning these encoders for downstream tasks require sufficiently large training data to converge or to achieve…

Computation and Language · Computer Science 2022-10-25 Hao Yang , Jinming Zhao , Gholamreza Haffari , Ehsan Shareghi

This paper proposes an end-to-end approach for single-channel speaker-independent multi-speaker speech separation, where time-frequency (T-F) masking, the short-time Fourier transform (STFT), and its inverse are represented as layers within…

Sound · Computer Science 2018-04-30 Zhong-Qiu Wang , Jonathan Le Roux , DeLiang Wang , John R. Hershey

Dynamic Magnetic Resonance Imaging (MRI) of the vocal tract has become an increasingly adopted imaging modality for speech motor studies. Beyond image signals, systematic data loss, noise pollution, and audio file corruption can occur due…

Sound · Computer Science 2025-12-02 Yaxuan Li , Han Jiang , Yifei Ma , Shihua Qin , Jonghye Woo , Fangxu Xing

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-05 Andy T. Liu , Shang-Wen Li , Hung-yi Lee

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

Sound · Computer Science 2025-07-18 Luca Della Libera , Cem Subakan , Mirco Ravanelli

The reconstruction mechanisms built by the human auditory system during sound reconstruction are still a matter of debate. The purpose of this study is to refine the auditory cortex model introduced in [9], and inspired by the geometrical…

Analysis of PDEs · Mathematics 2021-03-09 Rand Asswad , Ugo Boscain , Giuseppina Turco , Dario Prandi , Ludovic Sacchelli

Speech compression is commonly used to send voice over radio channels in applications such as mobile telephony and two-way push-to-talk (PTT) radio. In classical systems, the speech codec is combined with forward error correction,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-29 David Rowe , Jean-Marc Valin

In this work, we investigate the effectiveness of two techniques for improving variational autoencoder (VAE) based voice conversion (VC). First, we reconsider the relationship between vocoder features extracted using the high quality…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-09 Wen-Chin Huang , Yi-Chiao Wu , Chen-Chou Lo , Patrick Lumban Tobing , Tomoki Hayashi , Kazuhiro Kobayashi , Tomoki Toda , Yu Tsao , Hsin-Min Wang

Self-attention mechanisms have enabled transformers to achieve superhuman-level performance on many speech-to-text (STT) tasks, yet the challenge of automatic prosodic segmentation has remained unsolved. In this paper we finetune Whisper, a…

Computation and Language · Computer Science 2025-02-28 Nathan Roll , Calbert Graham , Simon Todd

B-mode ultrasound tongue imaging is widely used in the speech production field. However, efficient interpretation is in a great need for the tongue image sequences. Inspired by the recent success of unsupervised deep learning approach, we…

Image and Video Processing · Electrical Eng. & Systems 2019-03-05 Bo Li , Kele Xu , Dawei Feng , Haibo Mi , Huaimin Wang , Jian Zhu

Dysarthria speech contains the pathological characteristics of vocal tract and vocal fold, but so far, they have not yet been included in traditional acoustic feature sets. Moreover, the nonlinearity and non-stationarity of speech have been…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-02 Ting Zhu , Shufei Duan , Camille Dingam , Huizhi Liang , Wei Zhang

Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-28 Xinmeng Xu , Jianjun Hao

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

Source separation and other audio applications have traditionally relied on the use of short-time Fourier transforms as a front-end frequency domain representation step. The unavailability of a neural network equivalent to forward and…

Sound · Computer Science 2017-11-01 Shrikant Venkataramani , Jonah Casebeer , Paris Smaragdis

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Computation and Language · Computer Science 2023-05-17 Nurullah Sevim , Ege Ozan Özyedek , Furkan Şahinuç , Aykut Koç

Recent studies have explored the use of deep generative models of speech spectra based of variational autoencoders (VAEs), combined with unsupervised noise models, to perform speech enhancement. These studies developed iterative algorithms…

Sound · Computer Science 2019-05-15 Manuel Pariente , Antoine Deleforge , Emmanuel Vincent

Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Anmol Gulati , James Qin , Chung-Cheng Chiu , Niki Parmar , Yu Zhang , Jiahui Yu , Wei Han , Shibo Wang , Zhengdong Zhang , Yonghui Wu , Ruoming Pang

We propose an end-to-end speech enhancement method with trainable time-frequency~(T-F) transform based on invertible deep neural network~(DNN). The resent development of speech enhancement is brought by using DNN. The ordinary DNN-based…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-17 Daiki Takeuchi , Kohei Yatabe , Yuma Koizumi , Yasuhiro Oikawa , Noboru Harada