English
Related papers

Related papers: Differentiable Consistency Constraints for Improve…

200 papers

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

Recently, speech enhancement technologies that are based on deep learning have received considerable research attention. If the spatial information in microphone signals is exploited, microphone arrays can be advantageous under some adverse…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-19 Yicheng Hsu , Yonghan Lee , Mingsian R. Bai

Although supervised learning based on a deep neural network has recently achieved substantial improvement on speech enhancement, the existing schemes have either of two critical issues: spectrum or metric mismatches. The spectrum mismatch…

Sound · Computer Science 2020-05-12 Jaeyoung Kim , Mostafa El-Khamy , Jungwon Lee

In this work, we propose a novel consistency-preserving loss function for recovering the phase information in the context of phase reconstruction (PR) and speech enhancement (SE). Different from conventional techniques that directly…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Pin-Jui Ku , Chun-Wei Ho , Hao Yen , Sabato Marco Siniscalchi , Chin-Hui Lee

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

Recent works have shown that Deep Recurrent Neural Networks using the LSTM architecture can achieve strong single-channel speech enhancement by estimating time-frequency masks. However, these models do not naturally generalize to…

Sound · Computer Science 2020-12-04 Felix Grezes , Zhaoheng Ni , Viet Anh Trinh , Michael Mandel

For most of the state-of-the-art speech enhancement techniques, a spectrogram is usually preferred than the respective time-domain raw data since it reveals more compact presentation together with conspicuous temporal information over a…

Sound · Computer Science 2016-08-24 Syu-Siang Wang , Alan Chern , Yu Tsao , Jeih-weih Hung , Xugang Lu , Ying-Hui Lai , Borching Su

Recent advances in deep learning have significantly improved multichannel speech enhancement algorithms, yet conventional training loss functions such as the scale-invariant signal-to-distortion ratio (SDR) may fail to preserve fine-grained…

Sound · Computer Science 2025-06-24 Nasser-Eddine Monir , Paul Magron , Romain Serizel

Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-21 Heitor R. Guimarães , Ke Tan , Juan Azcarreta , Jesus Alvarez , Prabhav Agrawal , Ashutosh Pandey , Buye Xu

This paper introduces a dual-signal transformation LSTM network (DTLN) for real-time speech enhancement as part of the Deep Noise Suppression Challenge (DNS-Challenge). This approach combines a short-time Fourier transform (STFT) and a…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-23 Nils L. Westhausen , Bernd T. Meyer

Speech super-resolution (SSR) enhances low-resolution speech by increasing the sampling rate. While most SSR methods focus on magnitude reconstruction, recent research highlights the importance of phase reconstruction for improved…

Vocal dereverberation remains a challenging task in audio processing, particularly for real-time applications where both accuracy and efficiency are crucial. Traditional deep learning approaches often struggle to suppress reverberation…

Sound · Computer Science 2025-10-02 Daniel G. Williams

Fine-tuning large language models on downstream tasks is crucial for realizing their cross-domain potential but often relies on sensitive data, raising privacy concerns. Differential privacy (DP) offers rigorous privacy guarantees and has…

Machine Learning · Computer Science 2026-01-19 Lele Zheng , Xiang Wang , Tao Zhang , Yang Cao , Ke Cheng , Yulong Shen

Self-supervised representation learning (SSL) has attained SOTA results on several downstream speech tasks, but SSL-based speech enhancement (SE) solutions still lag behind. To address this issue, we exploit three main ideas: (i)…

Frame-online speech enhancement systems in the short-time Fourier transform (STFT) domain usually have an algorithmic latency equal to the window size due to the use of overlap-add in the inverse STFT (iSTFT). This algorithmic latency…

Sound · Computer Science 2022-07-13 Zhong-Qiu Wang , Shinji Watanabe

Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…

Sound · Computer Science 2025-11-14 Inbal Rimon , Oren Gal , Haim Permuter

Score-based generative models (SGMs) have recently shown impressive results for difficult generative tasks such as the unconditional and conditional generation of natural images and audio signals. In this work, we extend these models to the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-08 Simon Welker , Julius Richter , Timo Gerkmann

Stuttering is a speech impediment affecting tens of millions of people on an everyday basis. Even with its commonality, there is minimal data and research on the identification and classification of stuttered speech. This paper tackles the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-29 Tedd Kourkounakis , Amirhossein Hajavi , Ali Etemad

Recently, supervised speech separation has made great progress. However, limited by the nature of supervised training, most existing separation methods require ground-truth sources and are trained on synthetic datasets. This ground-truth…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-09 Jiangyu Han , Yanhua Long

Automatic recognition of disordered speech remains a highly challenging task to date. Sources of variability commonly found in normal speech including accent, age or gender, when further compounded with the underlying causes of speech…

Sound · Computer Science 2022-01-20 Mengzhe Geng , Shansong Liu , Jianwei Yu , Xurong Xie , Shoukang Hu , Zi Ye , Zengrui Jin , Xunying Liu , Helen Meng