English
Related papers

Related papers: DDSP-QbE++: Improving Speech Quality for Speech An…

200 papers

End-to-end singing voice synthesis (SVS) model VISinger can achieve better performance than the typical two-stage model with fewer parameters. However, VISinger has several problems: text-to-phase problem, the end-to-end model learns the…

Sound · Computer Science 2022-11-08 Yongmao Zhang , Heyang Xue , Hanzhao Li , Lei Xie , Tingwei Guo , Ruixiong Zhang , Caixia Gong

Machine learning based singing voice models require large datasets and lengthy training times. In this work we present a lightweight architecture, based on the Differentiable Digital Signal Processing (DDSP) library, that is able to output…

Sound · Computer Science 2021-03-15 Juan Alonso , Cumhur Erkut

Speech enhancement has recently achieved great success with various deep learning methods. However, most conventional speech enhancement systems are trained with supervised methods that impose two significant challenges. First, a majority…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-22 Viet Anh Trinh , Sebastian Braun

The reconstruction of clipped speech signals is an important task in audio signal processing to achieve an enhanced audio quality for further processing. In this paper, Frequency Selective Extrapolation (FSE), which is commonly used for…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-11 Markus Jonscher , Jürgen Seiler , André Kaup

Transformer-based audio self-supervised learning (SSL) models commonly use spectrograms, vision-style Transformers, and masked modeling objectives. However, convolutional patchification with temporal downsampling lowers the effective…

Sound · Computer Science 2026-05-15 Kohei Yamamoto , Kosuke Okusa

Recent progress in diffusion-based Singing Voice Synthesis (SVS) demonstrates strong expressiveness but remains limited by data scarcity and model scalability. We introduce a two-stage pipeline: a compact seed set of human-sung recordings…

A large and growing amount of speech content in real-life scenarios is being recorded on consumer-grade devices in uncontrolled environments, resulting in degraded speech quality. Transforming such low-quality device-degraded speech into…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-23 Haoyu Li , Junichi Yamagishi

Speech deepfake detection (SDD) systems perform well on standard benchmarks datasets but often fail to generalize to expressive and emotional spoofing attacks. Many methods rely on spoof-heavy training data, learning dataset-specific…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-16 Aurosweta Mahapatra , Ismail Rasim Ulgen , Kong Aik Lee , Nicholas Andrews , Berrak Sisman

Speech enhancement for voice pickup in hearables aims to improve the user's voice by suppressing noise and interfering talkers, while maintaining own-voice quality. For single-channel methods, it is particularly challenging to distinguish…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-05 Mattes Ohlenbusch , Mikolaj Kegler , Marko Stamenovic

In self-supervised learning, it is challenging to reduce the gap between the enhancement performance on the estimated and target speech signals with existed pre-tasks. In this paper, we propose a multi-task pre-training method to improve…

Sound · Computer Science 2022-01-02 Yi Li , Yang Sun , Syed Mohsen Naqvi

When the task of locating manipulation regions in partially-fake audio (PFA) involves cross-domain datasets, the performance of deep learning models drops significantly due to the shift between the source and target domains. To address this…

Sound · Computer Science 2024-07-12 Siding Zeng , Jiangyan Yi , Jianhua Tao , Yujie Chen , Shan Liang , Yong Ren , Xiaohui Zhang

In this paper, we propose a novel speech enhancement (SE) method by exploiting the discrete wavelet transform (DWT). This new method reduces the amount of fast time-varying portion, viz. the DWT-wise detail component, in the spectrogram of…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-09 Shih-kuang Lee , Syu-Siang Wang , Yu Tsao , Jeih-weih Hung

Speech deepfake detection (DFD) has benefited from diverse acoustic and semantic speech representations, many of which encode valuable speech information and are costly to train. Existing approaches typically enhance DFD by tuning the…

Sound · Computer Science 2026-02-26 Yupei Li , Chenyang Lyu , Longyue Wang , Weihua Luo , Kaifu Zhang , Björn W. Schuller

Using unsupervised learning to disentangle speech into content, rhythm, pitch, and timbre for voice conversion has become a hot research topic. Existing works generally take into account disentangling speech components through human-crafted…

Sound · Computer Science 2024-05-01 Ziqi Liang , Jianzong Wang , Xulong Zhang , Yong Zhang , Ning Cheng , Jing Xiao

Phase distortion refers to the alteration of the phase relationships between frequencies in a signal, which can be perceptible. In this paper, we discuss a special case of phase distortion known as phase-intercept distortion, which is…

Signal Processing · Electrical Eng. & Systems 2026-02-25 Venkatakrishnan Vaidyanathapuram Krishnan , Nathaniel Condit-Schultz

The performances of automatic speech recognition (ASR) systems degrade drastically under noisy conditions. Explicit distortion modelling (EDM), as a feature compensation step, is able to enhance ASR systems under such conditions by…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-02 Z. Guo , C. Chen , E. S. Chng

Many techniques in quantum control rely on frequency separation as a means for suppressing unwanted couplings. In its simplest form, the mechanism relies on the low bandwidth of control pulses of long duration. Here we perform a…

Quantum Physics · Physics 2015-06-17 Felix Motzoi , Frank K. Wilhelm

We present a self-supervised speech restoration method without paired speech corpora. Because the previous general speech restoration method uses artificial paired data created by applying various distortions to high-quality speech corpora,…

Achieving high perceptual quality without hallucination remains a challenge in generative speech enhancement (SE). A representative approach, PASE, is robust to hallucination but has limited perceptual quality under adverse conditions. We…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-11 Xiaobin Rong , Jun Gao , Zheng Wang , Mansur Yesilbursa , Kamil Wojcicki , Jing Lu

Modulations are a critical part of sound design and music production, enabling the creation of complex and evolving audio. Modern synthesizers provide envelopes, low frequency oscillators (LFOs), and more parameter automation tools that…

Sound · Computer Science 2025-10-08 Christopher Mitcheltree , Hao Hao Tan , Joshua D. Reiss