English
Related papers

Related papers: Sequence-to-sequence Singing Voice Synthesis with …

200 papers

Recent Text-to-Speech (TTS) systems trained on reading or acted corpora have achieved near human-level naturalness. The diversity of human speech, however, often goes beyond the coverage of these corpora. We believe the ability to handle…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-09 Li-Wei Chen , Shinji Watanabe , Alexander Rudnicky

Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with…

Sound · Computer Science 2025-07-04 Wan Lin , Junhui Chen , Tianhao Wang , Zhenyu Zhou , Lantian Li , Dong Wang

We present several methods to improve the generalisation of language identification (LID) systems to new speakers and to new domains. These methods involve Spectral augmentation, where spectrograms are masked in the frequency or time bands…

Sound · Computer Science 2020-12-08 Ruan van der Merwe

Recent speech enhancement (SE) models increasingly leverage self-supervised learning (SSL) representations for their rich semantic information. Typically, intermediate features are aggregated into a single representation via a lightweight…

Sound · Computer Science 2026-02-02 Seungu Han , Sungho Lee , Kyogu Lee

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

Personalized speech enhancement (PSE) has shown convincing results when it comes to extracting a known target voice among interfering ones. The corresponding systems usually incorporate a representation of the target voice within the…

Sound · Computer Science 2026-01-26 Thomas Serre , Mathieu Fontaine , Éric Benhaim , Slim Essid

In this work, we present an end-to-end binaural speech synthesis system that combines a low-bitrate audio codec with a powerful binaural decoder that is capable of accurate speech binauralization while faithfully reconstructing…

Sound · Computer Science 2022-07-11 Wen Chin Huang , Dejan Markovic , Alexander Richard , Israel Dejene Gebru , Anjali Menon

End-to-end (E2E) automatic speech recognition (ASR) models have recently demonstrated superior performance over the traditional hybrid ASR models. Training an E2E ASR model requires a large amount of data which is not only expensive but may…

Machine Learning · Computer Science 2021-06-16 Amin Fazel , Wei Yang , Yulan Liu , Roberto Barra-Chicote , Yixiong Meng , Roland Maas , Jasha Droppo

Single-channel speech enhancement approaches do not always improve automatic recognition rates in the presence of noise, because they can introduce distortions unhelpful for recognition. Following a trend towards end-to-end training of…

Sound · Computer Science 2021-12-14 Peter Plantinga , Deblin Bagchi , Eric Fosler-Lussier

The lack of a publicly-available large-scale and diverse dataset has long been a significant bottleneck for singing voice applications like Singing Voice Synthesis (SVS) and Singing Voice Conversion (SVC). To tackle this problem, we present…

Sound · Computer Science 2025-05-15 Yicheng Gu , Chaoren Wang , Junan Zhang , Xueyao Zhang , Zihao Fang , Haorui He , Zhizheng Wu

With just a few speech samples, it is possible to perfectly replicate a speaker's voice in recent years, while malicious voice exploitation (e.g., telecom fraud for illegal financial gain) has brought huge hazards in our daily lives.…

Sound · Computer Science 2024-10-29 Zhisheng Zhang , Qianyi Yang , Derui Wang , Pengyang Huang , Yuxin Cao , Kai Ye , Jie Hao

Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage…

Audio and Speech Processing · Electrical Eng. & Systems 2018-07-24 Mahdi Hajibabaei , Dengxin Dai

High-quality singing annotations are fundamental to modern Singing Voice Synthesis (SVS) systems. However, obtaining these annotations at scale through manual labeling is unrealistic due to the substantial labor and musical expertise…

Sound · Computer Science 2026-05-07 Yukun Chen , Tianrui Wang , Zhaoxi Mu , Xinyu Yang , EngSiong Chng

Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…

Sound · Computer Science 2021-03-18 Jeff Donahue , Sander Dieleman , Mikołaj Bińkowski , Erich Elsen , Karen Simonyan

Deep generative models have achieved significant progress in speech synthesis to date, while high-fidelity singing voice synthesis is still an open problem for its long continuous pronunciation, rich high-frequency parts, and strong…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-08 Rongjie Huang , Chenye Cui , Feiyang Chen , Yi Ren , Jinglin Liu , Zhou Zhao , Baoxing Huai , Zhefeng Wang

Because videos in the wild can be out of sync for various reasons, a sync-net is used to bring the video back into sync for tasks that require synchronized videos. Previous state-of-the-art (SOTA) sync-nets use InfoNCE loss, rely on the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-05 Sungjoon Park , Jaesub Yun , Donggeon Lee , Minsik Park

Labeling a training set is often expensive and susceptible to errors, making the design of robust loss functions for label noise an important problem. The symmetry condition provides theoretical guarantees for robustness to such noise. In…

Machine Learning · Computer Science 2026-05-21 Alexandre Lemire Paquin , Brahim Chaib-Draa , Philippe Giguère

End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employing the standard pipeline composed of a separately trained…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-22 Loren Lugosch , Brett Meyer , Derek Nowrouzezahrai , Mirco Ravanelli

We present a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the influence of pitch and timbre.…

Sound · Computer Science 2017-08-18 Merlijn Blaauw , Jordi Bonada

Speaker adaptation methods aim to create fair quality synthesis speech voice font for target speakers while only limited resources available. Recently, as deep neural networks based statistical parametric speech synthesis (SPSS) methods…

Audio and Speech Processing · Electrical Eng. & Systems 2018-03-08 Zhiying Huang , Heng Lu , Ming Lei , Zhijie Yan