English
Related papers

Related papers: SPADE: Self-supervised Pretraining for Acoustic Di…

200 papers

In this paper, we propose the use of self-supervised pretraining on a large unlabelled data set to improve the performance of a personalized voice activity detection (VAD) model in adverse conditions. We pretrain a long short-term memory…

Sound · Computer Science 2024-01-24 Holger Severin Bovbjerg , Jesper Jensen , Jan Østergaard , Zheng-Hua Tan

End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-28 Pu Wang , Hugo Van hamme

We present a new approach to disentangle speaker voice and phone content by introducing new components to the VQ-VAE architecture for speech synthesis. The original VQ-VAE does not generalize well to unseen speakers or content. To alleviate…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-11 Jennifer Williams , Yi Zhao , Erica Cooper , Junichi Yamagishi

In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-29 Danwei Cai , Weiqing Wang , Ming Li

We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functions. We perform experiments on the standard LibriSpeech…

Nowadays, recognition-synthesis-based methods have been quite popular with voice conversion (VC). By introducing linguistics features with good disentangling characters extracted from an automatic speech recognition (ASR) model, the VC…

Sound · Computer Science 2023-05-17 Xintao Zhao , Shuai Wang , Yang Chao , Zhiyong Wu , Helen Meng

Due to the lack of target speech annotations in real-recorded far-field conversational datasets, speech enhancement (SE) models are typically trained on simulated data. However, the trained models often perform poorly in real-world…

Sound · Computer Science 2025-06-24 Longjie Luo , Lin Li , Qingyang Hong

In this work, we provide a broad comparative analysis of strategies for pre-training audio understanding models for several tasks in the music domain, including labelling of genre, era, origin, mood, instrumentation, key, pitch, vocal…

Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Danwei Cai , Zexin Cai , Ze Li , Ming Li

Existing studies on self-supervised speech representation learning have focused on developing new training methods and applying pre-trained models for different applications. However, the quality of these models is often measured by the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-18 Alexander H. Liu , Sung-Lin Yeh , James Glass

This paper tackles the scarcity of benchmarking data in disentangled auditory representation learning. We introduce SynTone, a synthetic dataset with explicit ground truth explanatory factors for evaluating disentanglement techniques.…

Sound · Computer Science 2024-02-19 Yusuf Brima , Ulf Krumnack , Simone Pika , Gunther Heidemann

Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a…

Sound · Computer Science 2024-08-28 Yiqiang Cai , Shengchen Li , Xi Shao

Disentangling speaker and content attributes of a speech signal into separate latent representations followed by decoding the content with an exchanged speaker representation is a popular approach for voice conversion, which can be trained…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-07 Michael Kuhlmann , Fritz Seebauer , Janek Ebbers , Petra Wagner , Reinhold Haeb-Umbach

Recently, deep representation learning has shown strong performance in multiple audio tasks. However, its use for learning spatial representations from multichannel audio is underexplored. We investigate the use of a pretraining stage based…

Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks…

Sound · Computer Science 2026-04-02 Xiaoxu Zhu , Junhua Li , Aaron J. Li , Guangchao Yao , Xiaojie Yu

The fast increase of web services and mobile apps, which collect personal data from users, increases the risk that their privacy may be severely compromised. In particular, the increasing variety of spoken language interfaces and voice…

Self-supervised learning can significantly improve the performance of downstream tasks, however, the dimensions of learned representations normally lack explicit physical meanings. In this work, we propose a novel self-supervised approach…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-19 Yifan Sun , Xihong Wu

In speech technologies, speaker's voice representation is used in many applications such as speech recognition, voice conversion, speech synthesis and, obviously, user authentication. Modern vocal representations of the speaker are based on…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-17 Paul-Gauthier Noé , Mohammad Mohammadamini , Driss Matrouf , Titouan Parcollet , Andreas Nautsch , Jean-François Bonastre

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

Audio pretrained models are widely employed to solve various tasks in speech processing, sound event detection, or music information retrieval. However, the representations learned by these models are unclear, and their analysis mainly…

‹ Prev 1 4 5 6 7 8 10 Next ›