English
Related papers

Related papers: Mel-FullSubNet: Mel-Spectrogram Enhancement for Im…

200 papers

Quality and intelligibility of speech signals are degraded under additive background noise which is a critical problem for hearing aid and cochlear implant users. Motivated to address this problem, we propose a novel speech enhancement…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-06 Hamidreza Baradaran Kashani , Ata Jodeiri , Mohammad Mohsen Goodarzi , Iman Sarraf Rezaei

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

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 based on a rigorous…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-14 Yoshiki Masuyama , Natsuki Ueno , Nobutaka Ono

This paper describes multichannel speech enhancement for improving automatic speech recognition (ASR) in noisy environments. Recently, the minimum variance distortionless response (MVDR) beamforming has widely been used because it works…

Automatic speech recognition (ASR) systems are of vital importance nowadays in commonplace tasks such as speech-to-text processing and language translation. This created the need for an ASR system that can operate in realistic crowded…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-29 Sherif Abdulatif , Karim Armanious , Karim Guirguis , Jayasankar T. Sajeev , Bin Yang

We study speech enhancement using deep learning (DL) for virtual meetings on cellular devices, where transmitted speech has background noise and transmission loss that affects speech quality. Since the Deep Noise Suppression (DNS) Challenge…

Sound · Computer Science 2023-02-17 Hojeong Lee , Minseon Gwak , Kawon Lee , Minjeong Kim , Joseph Konan , Ojas Bhargave

We present improvements in automatic speech recognition (ASR) for Somali, a currently extremely under-resourced language. This forms part of a continuing United Nations (UN) effort to employ ASR-based keyword spotting systems to support…

Computation and Language · Computer Science 2019-07-09 Astik Biswas , Raghav Menon , Ewald van der Westhuizen , Thomas Niesler

This work proposes a new learning target based on reverberation time shortening (RTS) for speech dereverberation. The learning target for dereverberation is usually set as the direct-path speech or optionally with some early reflections.…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-22 Rui Zhou , Wenye Zhu , Xiaofei Li

Recent research has successfully adapted vision-based convolutional neural network (CNN) architectures for audio recognition tasks using Mel-Spectrograms. However, these CNNs have high computational costs and memory requirements, limiting…

Sound · Computer Science 2024-04-23 Kin Wai Lau , Yasar Abbas Ur Rehman , Lai-Man Po

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a…

Computation and Language · Computer Science 2026-02-24 Zefang Liu , Chenyang Zhu , Sangwoo Cho , Shi-Xiong Zhang

We introduce CrossNet, a complex spectral mapping approach to speaker separation and enhancement in reverberant and noisy conditions. The proposed architecture comprises an encoder layer, a global multi-head self-attention module, a…

Sound · Computer Science 2024-03-07 Vahid Ahmadi Kalkhorani , DeLiang Wang

Due to the successful application of deep learning, audio spoofing detection has made significant progress. Spoofed audio with speech synthesis or voice conversion can be well detected by many countermeasures. However, an automatic speaker…

Sound · Computer Science 2024-01-12 Lian Huang , Chi-Man Pun

Large scale machine learning (ML) systems such as the Alexa automatic speech recognition (ASR) system continue to improve with increasing amounts of manually transcribed training data. Instead of scaling manual transcription to impractical…

This work proposes a new learning target based on reverberation time shortening (RTS) for speech dereverberation. The learning target for dereverberation is usually set as the direct-path speech or optionally with some early reflections.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-07 Rui Zhou , Wenye Zhu , Xiaofei Li

Noise suppression systems generally produce output speech with compromised quality. We propose to utilize the high quality speech generation capability of neural vocoders for noise suppression. We use a neural network to predict clean…

Sound · Computer Science 2019-11-15 Soumi Maiti , Michael I Mandel

We investigate the effectiveness of generative adversarial networks (GANs) for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR) systems. Prior work demonstrates that GANs can effectively…

Sound · Computer Science 2018-11-01 Chris Donahue , Bo Li , Rohit Prabhavalkar

Decoding speech from brain signals is a challenging research problem. Although existing technologies have made progress in reconstructing the mel spectrograms of auditory stimuli at the word or letter level, there remain core challenges in…

Sound · Computer Science 2025-08-12 Cunhang Fan , Sheng Zhang , Jingjing Zhang , Enrui Liu , Xinhui Li , Gangming Zhao , Zhao Lv

Enhancing noisy speech is an important task to restore its quality and to improve its intelligibility. In traditional non-machine-learning (ML) based approaches the parameters required for noise reduction are estimated blindly from the…

Sound · Computer Science 2018-01-16 Robert Rehr , Timo Gerkmann

This paper presents our latest investigation on Densely Connected Convolutional Networks (DenseNets) for acoustic modelling (AM) in automatic speech recognition. DenseN-ets are very deep, compact convolutional neural networks, which have…

Computation and Language · Computer Science 2018-08-13 Chia Yu Li , Ngoc Thang Vu

This paper presents a novel neural vocoder named APNet which reconstructs speech waveforms from acoustic features by predicting amplitude and phase spectra directly. The APNet vocoder is composed of an amplitude spectrum predictor (ASP) and…

Sound · Computer Science 2023-05-16 Yang Ai , Zhen-Hua Ling