English
Related papers

Related papers: Masked Autoencoders as Universal Speech Enhancer

200 papers

Single-channel speech enhancement is utilized in various tasks to mitigate the effect of interfering signals. Conventionally, to ensure the speech enhancement performs optimally, the speech enhancement has needed to be tuned for each task.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-11 Hiroshi Sato , Tsubasa Ochiai , Marc Delcroix , Takafumi Moriya , Takanori Ashihara , Ryo Masumura

Recent Self-Supervised Learning (SSL) methods are able to learn feature representations that are invariant to different data augmentations, which can then be transferred to downstream tasks of interest. However, different downstream tasks…

Machine Learning · Computer Science 2023-03-08 Chen Huang , Hanlin Goh , Jiatao Gu , Josh Susskind

Since the introduction of Masked Autoencoders, various improvements to masking techniques have been explored. In this paper, we rethink masking strategies for audio representation learning using masked prediction-based self-supervised…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-26 Daisuke Niizumi , Daiki Takeuchi , Masahiro Yasuda , Binh Thien Nguyen , Noboru Harada , Nobutaka Ono

In this paper, we propose a simple yet powerful improvement over the recent Self-Supervised Audio Spectrogram Transformer (SSAST) model for speech and audio classification. Specifically, we leverage the insight that the SSAST uses a very…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-01 Alan Baade , Puyuan Peng , David Harwath

Deep learning-based models have greatly advanced the performance of speech enhancement (SE) systems. However, two problems remain unsolved, which are closely related to model generalizability to noisy conditions: (1) mismatched noisy…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-29 Cheng Yu , Ryandhimas E. Zezario , Syu-Siang Wang , Jonathan Sherman , Yi-Yen Hsieh , Xugang Lu , Hsin-Min Wang , Yu Tsao

Supervised learning for single-channel speech enhancement requires carefully labeled training examples where the noisy mixture is input into the network and the network is trained to produce an output close to the ideal target. To relax the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-19 Yu-Che Wang , Shrikant Venkataramani , Paris Smaragdis

Self-supervised learning (SSL) using masked prediction has made great strides in general-purpose audio representation. This study proposes Masked Modeling Duo (M2D), an improved masked prediction SSL, which learns by predicting…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-10 Daisuke Niizumi , Daiki Takeuchi , Yasunori Ohishi , Noboru Harada , Kunio Kashino

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…

We introduce AnyEnhance, a unified generative model for voice enhancement that processes both speech and singing voices. Based on a masked generative model, AnyEnhance is capable of handling both speech and singing voices, supporting a wide…

Sound · Computer Science 2025-11-04 Junan Zhang , Jing Yang , Zihao Fang , Yuancheng Wang , Zehua Zhang , Zhuo Wang , Fan Fan , Zhizheng Wu

Self-supervised learning (SSL) has grown in interest within the speech processing community, since it produces representations that are useful for many downstream tasks. SSL uses global and contextual methods to produce robust…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-08 Subrina Sultana , Donald S. Williamson

Recently, self-supervised learning (SSL) techniques have been introduced to solve the monaural speech enhancement problem. Due to the lack of using clean phase information, the enhancement performance is limited in most SSL methods.…

Sound · Computer Science 2021-12-22 Yi Li , Yang Sun , Syed Mohsen Naqvi

Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-06 Xiaoran Fan , Chao Pang , Tian Yuan , He Bai , Renjie Zheng , Pengfei Zhu , Shuohuan Wang , Junkun Chen , Zeyu Chen , Liang Huang , Yu Sun , Hua Wu

In this work, we present an analysis of a DNN-based autoencoder for speech enhancement, dereverberation and denoising. The target application is a robust speaker verification (SV) system. We start our approach by carefully designing a data…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-20 Ondrej Novotny , Oldrich Plchot , Ondrej Glembek , Jan "Honza" Cernocky , Lukas Burget

We investigated the adaptation and performance of Masked Autoencoders (MAEs) with Vision Transformer (ViT) architectures for self-supervised representation learning on one-dimensional (1D) ultrasound signals. Although MAEs have demonstrated…

Machine Learning · Computer Science 2025-08-29 Immanuel Roßteutscher , Klaus S. Drese , Thorsten Uphues

Personalized speech enhancement (PSE) models can improve the audio quality of teleconferencing systems by adapting to the characteristics of a speaker's voice. However, most existing methods require a separate speaker embedding model to…

Sound · Computer Science 2024-06-17 Tanel Pärnamaa , Ando Saabas

Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale unlabeled audio data. While recent advances have been driven mainly by generative reconstruction objectives, contrastive approaches remain…

Machine Learning · Computer Science 2026-05-15 Hanxun Huang , Qizhou Wang , Xingjun Ma , Cihang Xie , Christopher Leckie , Sarah Erfani

We present a method for transferring pre-trained self-supervised (SSL) speech representations to multiple languages. There is an abundance of unannotated speech, so creating self-supervised representations from raw audio and fine-tuning on…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-08 Samuel Kessler , Bethan Thomas , Salah Karout

We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM). Given an input text with…

Computation and Language · Computer Science 2020-03-02 Hangbo Bao , Li Dong , Furu Wei , Wenhui Wang , Nan Yang , Xiaodong Liu , Yu Wang , Songhao Piao , Jianfeng Gao , Ming Zhou , Hsiao-Wuen Hon

This study explores using embedding rank as an unsupervised evaluation metric for general-purpose speech encoders trained via self-supervised learning (SSL). Traditionally, assessing the performance of these encoders is resource-intensive…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-22 Zakaria Aldeneh , Vimal Thilak , Takuya Higuchi , Barry-John Theobald , Tatiana Likhomanenko

The past decade has witnessed substantial growth of data-driven speech enhancement (SE) techniques thanks to deep learning. While existing approaches have shown impressive performance in some common datasets, most of them are designed only…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-19 Wangyou Zhang , Kohei Saijo , Zhong-Qiu Wang , Shinji Watanabe , Yanmin Qian