English
Related papers

Related papers: Towards Leveraging Sequential Structure in Animal …

200 papers

We propose vq-wav2vec to learn discrete representations of audio segments through a wav2vec-style self-supervised context prediction task. The algorithm uses either a gumbel softmax or online k-means clustering to quantize the dense…

Computation and Language · Computer Science 2020-02-18 Alexei Baevski , Steffen Schneider , Michael Auli

Unsupervised speech disentanglement aims at separating fast varying from slowly varying components of a speech signal. In this contribution, we take a closer look at the embedding vector representing the slowly varying signal components,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-20 Frederik Rautenberg , Michael Kuhlmann , Jana Wiechmann , Fritz Seebauer , Petra Wagner , Reinhold Haeb-Umbach

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. This paper proposes a hierarchical network with transformer encoders and memory mechanism to address this problem. The proposed…

Sound · Computer Science 2020-11-02 Yanpei Shi , Mingjie Chen , Qiang Huang , Thomas Hain

The distributed and continuous representations used by neural networks are at odds with representations employed in linguistics, which are typically symbolic. Vector quantization has been proposed as a way to induce discrete neural…

Computation and Language · Computer Science 2021-09-17 Bertrand Higy , Lieke Gelderloos , Afra Alishahi , Grzegorz Chrupała

Discrete audio representation, aka audio tokenization, has seen renewed interest driven by its potential to facilitate the application of text language modeling approaches in audio domain. To this end, various compression and…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-21 Krishna C. Puvvada , Nithin Rao Koluguri , Kunal Dhawan , Jagadeesh Balam , Boris Ginsburg

How to best develop foundational models for time series forecasting remains an important open question. Tokenization is a crucial consideration in this effort: what is an effective discrete vocabulary for a real-valued sequential input? To…

Typically, singing voice conversion (SVC) depends on an embedding vector, extracted from either a speaker lookup table (LUT) or a speaker recognition network (SRN), to model speaker identity. However, singing contains more expressive…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-07 Xu Li , Shansong Liu , Ying Shan

Generally speaking, the main objective when training a neural speech synthesis system is to synthesize natural and expressive speech from the output layer of the neural network without much attention given to the hidden layers. However, by…

Sound · Computer Science 2021-06-28 Hieu-Thi Luong , Junichi Yamagishi

With recent rapid growth of large language models (LLMs), discrete speech tokenization has played an important role for injecting speech into LLMs. However, this discretization gives rise to a loss of information, consequently impairing…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-23 Zhichao Huang , Chutong Meng , Tom Ko

The human perception system is often assumed to recruit motor knowledge when processing auditory speech inputs. Using articulatory modeling and deep learning, this study examines how this articulatory information can be used for discovering…

Computation and Language · Computer Science 2022-06-20 Marc-Antoine Georges , Jean-Luc Schwartz , Thomas Hueber

Applying x-vectors for speaker verification has recently attracted great interest, with the focus being on text-independent speaker verification. In this paper, we study x-vectors for text-dependent speaker verification (TD-SV), which…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-02 Achintya Kumar Sarkar , Zheng-Hua Tan

We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method…

Audio and Speech Processing · Electrical Eng. & Systems 2019-05-29 Marco Tagliasacchi , Beat Gfeller , Félix de Chaumont Quitry , Dominik Roblek

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…

Sound · Computer Science 2021-04-26 Chau Luu , Peter Bell , Steve Renals

The adoption of advanced deep learning architectures in stuttering detection (SD) tasks is challenging due to the limited size of the available datasets. To this end, this work introduces the application of speech embeddings extracted from…

Sound · Computer Science 2023-06-02 Shakeel A. Sheikh , Md Sahidullah , Fabrice Hirsch , Slim Ouni

In a noisy environment, a lossy speech signal can be automatically restored by a listener if he/she knows the language well. That is, with the built-in knowledge of a "language model", a listener may effectively suppress noise interference…

Machine Learning · Computer Science 2019-07-03 Chien-Feng Liao , Yu Tsao , Xugang Lu , Hisashi Kawai

Textless self-supervised speech models have grown in capabilities in recent years, but the nature of the linguistic information they encode has not yet been thoroughly examined. We evaluate the extent to which these models' learned…

Computation and Language · Computer Science 2023-06-13 Kinan Martin , Jon Gauthier , Canaan Breiss , Roger Levy

The temporal dynamics of speech, encompassing variations in rhythm, intonation, and speaking rate, contain important and unique information about speaker identity. This paper proposes a new method for representing speaker characteristics by…

Sound · Computer Science 2025-07-22 Natalia Tomashenko , Emmanuel Vincent , Marc Tommasi

The reliability of segmentation models in the medical domain depends on the model's robustness to perturbations in the input space. Robustness is a particular challenge in medical imaging exhibiting various sources of image noise,…

Image and Video Processing · Electrical Eng. & Systems 2022-07-06 Ainkaran Santhirasekaram , Avinash Kori , Mathias Winkler , Andrea Rockall , Ben Glocker

Vector-space word representations obtained from neural network models have been shown to enable semantic operations based on vector arithmetic. In this paper, we explore the existence of similar information on vector representations of…

Computer Vision and Pattern Recognition · Computer Science 2016-12-19 D. Garcia-Gasulla , J. Béjar , U. Cortés , E. Ayguadé , J. Labarta , T. Suzumura , R. Chen

Animals hear and vocalize across frequency ranges that differ substantially from humans, often extending into the ultrasonic domain. Yet most computational bioacoustics systems rely on audio models pre-trained at 16 kHz, restricting their…