English
Related papers

Related papers: A2SB: Audio-to-Audio Schrodinger Bridges

200 papers

Speech tokenizers are foundational to speech language models, yet existing approaches face two major challenges: (1) balancing trade-offs between encoding semantics for understanding and acoustics for reconstruction, and (2) achieving low…

The aim of this work is to investigate the impact of crossmodal self-supervised pre-training for speech reconstruction (video-to-audio) by leveraging the natural co-occurrence of audio and visual streams in videos. We propose LipSound2…

Sound · Computer Science 2022-09-13 Leyuan Qu , Cornelius Weber , Stefan Wermter

In this study, we propose a deep neural network for reconstructing intelligible speech from silent lip movement videos. We use auditory spectrogram as spectral representation of speech and its corresponding sound generation method resulting…

Computer Vision and Pattern Recognition · Computer Science 2017-10-27 Hassan Akbari , Himani Arora , Liangliang Cao , Nima Mesgarani

While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose…

Computation and Language · Computer Science 2023-05-30 Chen Xu , Yuhao Zhang , Chengbo Jiao , Xiaoqian Liu , Chi Hu , Xin Zeng , Tong Xiao , Anxiang Ma , Huizhen Wang , JingBo Zhu

This research project investigates the application of deep learning to timbre transfer, where the timbre of a source audio can be converted to the timbre of a target audio with minimal loss in quality. The adopted approach combines…

Sound · Computer Science 2021-10-12 Russell Sammut Bonnici , Charalampos Saitis , Martin Benning

Audio fingerprinting is a well-established solution for song identification from short recording excerpts. Popular methods rely on the extraction of sparse representations, generally spectral peaks, and have proven to be accurate, fast, and…

Sound · Computer Science 2023-10-31 Kamil Akesbi , Dorian Desblancs , Benjamin Martin

We present an end-to-end method for transforming audio from one style to another. For the case of speech, by conditioning on speaker identities, we can train a single model to transform words spoken by multiple people into multiple target…

Sound · Computer Science 2018-06-08 Albert Haque , Michelle Guo , Prateek Verma

Large diffusion models have been successful in text-to-audio (T2A) synthesis tasks, but they often suffer from common issues such as semantic misalignment and poor temporal consistency due to limited natural language understanding and data…

Controlling audible sound requires inherently broadband and subwavelength acoustic solutions, which are to date, crucially missing. This includes current noise absorption methods, such as porous materials or acoustic resonators, which are…

Applied Physics · Physics 2023-05-26 Stanislav Sergeev , Hervé Lissek , Romain Fleury

Video-to-audio (V2A) generation aims to synthesize content-matching audio from silent video, and it remains challenging to build V2A models with high generation quality, efficiency, and visual-audio temporal synchrony. We propose Frieren, a…

Sound · Computer Science 2025-01-07 Yongqi Wang , Wenxiang Guo , Rongjie Huang , Jiawei Huang , Zehan Wang , Fuming You , Ruiqi Li , Zhou Zhao

The development of models for quality prediction of both audio and video signals is a fairly mature field. But, although several multimodal models have been proposed, the area of audio-visual quality prediction is still an emerging area. In…

Multimedia · Computer Science 2020-02-06 Helard Martinez , M. C. Farias , A. Hines

For the difficulty and large computational complexity of modeling more frequency bands, full-band speech enhancement based on deep neural networks is still challenging. Previous studies usually adopt compressed full-band speech features in…

Sound · Computer Science 2022-08-02 Guochen Yu , Yuansheng Guan , Weixin Meng , Chengshi Zheng , Hui Wang

We study nonparametric estimation of Schr\"odinger bridge (SB) drifts from i.i.d.\ data observed on a single time interval. Starting from the conditional-ratio form of the Schr\"odinger bridge time-series (SBTS) drift formula, we analyze a…

Statistics Theory · Mathematics 2026-05-08 Othmane Mazhar , Huyên Pham

While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on…

Computation and Language · Computer Science 2020-03-25 Alex Bie , Bharat Venkitesh , Joao Monteiro , Md. Akmal Haidar , Mehdi Rezagholizadeh

This paper proposes an efficient reconfigurable hardware design for speech enhancement based on multi band spectral subtraction algorithm and involving both magnitude and phase components. Our proposed design is novel as it estimates…

Sound · Computer Science 2015-08-26 Tanmay Biswas , Sudhindu Bikash Mandal , Debasree Saha , Amlan Chakrabarti

Schroeder diffuser is a classical design, proposed over 40 years ago, for artificially creating optimal and predictable sound diffuse reflection. It has been widely adopted in architectural acoustics and it has also shown substantial…

Classical Physics · Physics 2017-06-14 Yifan Zhu , Xudong Fan , Bin Liang , Jianchun Cheng , Yun Jing

In this paper, a deep-learning-based method for sound field reconstruction is proposed. It is shown the possibility to reconstruct the magnitude of the sound pressure in the frequency band 30-300 Hz for an entire room by using a very low…

Sound · Computer Science 2020-08-07 Francesc Lluís , Pablo Martínez-Nuevo , Martin Bo Møller , Sven Ewan Shepstone

To scale neural speech synthesis to various real-world languages, we present a multilingual end-to-end framework that maps byte inputs to spectrograms, thus allowing arbitrary input scripts. Besides strong results on 40+ languages, the…

Computation and Language · Computer Science 2021-07-12 Mutian He , Jingzhou Yang , Lei He , Frank K. Soong

While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-19 Michael Gref , Oliver Walter , Christoph Schmidt , Sven Behnke , Joachim Köhler

Swiss German is a low-resource language represented by diverse dialects that differ significantly from Standard German and from each other, lacking a standardized written form. As a result, transcribing Swiss German involves translating…

Computation and Language · Computer Science 2025-06-11 Flavio D'Intino , Hans-Peter Hutter