English
Related papers

Related papers: On Compressing Sequences for Self-Supervised Speec…

200 papers

Traditional scaling laws in natural language processing suggest that increasing model size and training data enhances performance. However, recent studies reveal deviations, particularly in large language models, where performance…

Machine Learning · Computer Science 2025-07-16 Zhengyu Chen , Siqi Wang , Teng Xiao , Yudong Wang , Shiqi Chen , Xunliang Cai , Junxian He , Jingang Wang

We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-09 Alec Radford , Jong Wook Kim , Tao Xu , Greg Brockman , Christine McLeavey , Ilya Sutskever

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Ho Man Kwan , Shenghui Song

The Sparsespeech model is an unsupervised acoustic model that can generate discrete pseudo-labels for untranscribed speech. We extend the Sparsespeech model to allow for sampling over a random discrete variable, yielding…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-01 Benjamin Milde , Chris Biemann

Self-supervised learning (SSL) models usually require weeks of pre-training with dozens of high-end GPUs. These models typically have a multi-headed self-attention (MHSA) context encoder. However, MHSA takes quadratic time and space in the…

Computation and Language · Computer Science 2024-07-19 Shucong Zhang , Titouan Parcollet , Rogier van Dalen , Sourav Bhattacharya

Although deep neural networks have achieved remarkable results for the task of semantic segmentation, they usually fail to generalize towards new domains, especially when performing synthetic-to-real adaptation. Such domain shift is…

Computer Vision and Pattern Recognition · Computer Science 2021-10-07 Adriano Cardace , Pierluigi Zama Ramirez , Samuele Salti , Luigi Di Stefano

Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in…

Computation and Language · Computer Science 2021-04-12 Michael A. Hedderich , Lukas Lange , Heike Adel , Jannik Strötgen , Dietrich Klakow

Spectrograms - time-frequency representations of audio signals - have found widespread use in neural network-based spoofing detection. While deep models are trained on the fullband spectrum of the signal, we argue that not all frequency…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-07 Bhusan Chettri , Tomi Kinnunen , Emmanouil Benetos

There has been a growing trend in compressing and transmitting videos from terminals for machine vision tasks. Nevertheless, most video coding optimization method focus on minimizing distortion according to human perceptual metrics,…

Multimedia · Computer Science 2025-12-18 Fei Zhao , Mengxi Guo , Shijie Zhao , Junlin Li , Li Zhang , Xiaodong Xie

Recent advances in deep learning have markedly improved the quality of visual-attention modelling. In this work we apply these advances to video compression. We propose a compression method that uses a saliency model to adaptively compress…

Computer Vision and Pattern Recognition · Computer Science 2019-07-25 Vitaliy Lyudvichenko , Mikhail Erofeev , Alexander Ploshkin , Dmitriy Vatolin

Personalized speech enhancement (PSE) models utilize additional cues, such as speaker embeddings like d-vectors, to remove background noise and interfering speech in real-time and thus improve the speech quality of online video conferencing…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-20 Sefik Emre Eskimez , Takuya Yoshioka , Huaming Wang , Xiaofei Wang , Zhuo Chen , Xuedong Huang

Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various data augmentation…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-11 Salah Zaiem , Titouan Parcollet , Slim Essid

End-to-end speech summarization has been shown to improve performance over cascade baselines. However, such models are difficult to train on very large inputs (dozens of minutes or hours) owing to compute restrictions and are hence trained…

Computation and Language · Computer Science 2023-07-18 Roshan Sharma , Kenneth Zheng , Siddhant Arora , Shinji Watanabe , Rita Singh , Bhiksha Raj

Audio captioning is the task of automatically creating a textual description for the contents of a general audio signal. Typical audio captioning methods rely on deep neural networks (DNNs), where the target of the DNN is to map the input…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-08 Khoa Nguyen , Konstantinos Drossos , Tuomas Virtanen

Parameter-efficient tuning aims to mitigate the large memory requirements of adapting pretrained language models for downstream tasks. For example, one popular method, prefix-tuning, prepends trainable tokens to sequences while freezing the…

Computation and Language · Computer Science 2023-05-26 Jonathan Li , Will Aitken , Rohan Bhambhoria , Xiaodan Zhu

In recent years, advances in Artificial Intelligence have significantly impacted computer science, particularly in the field of computer vision, enabling solutions to complex problems such as video frame prediction. Video frame prediction…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Jose M. Sánchez Velázquez , Mingbo Cai , Andrew Coney , Álvaro J. García- Tejedor , Alberto Nogales

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

In music and speech, meaning is derived at multiple levels of context. Affect, for example, can be inferred both by a short sound token and by sonic patterns over a longer temporal window such as an entire recording. In this letter, we…

Sound · Computer Science 2022-09-12 Camille Noufi , Prateek Verma

When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world computing systems do not always provide stable resource…

Machine Learning · Computer Science 2021-10-11 Elvis Nunez , Maxwell Horton , Anish Prabhu , Anurag Ranjan , Ali Farhadi , Mohammad Rastegari

Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving…