paper-with-me

Papers

Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning

2022-04-11 · Robin Algayres, Adel Nabli, Benoit Sagot, Emmanuel Dupoux

We introduce a simple neural encoder architecture that can be trained using an unsupervised contrastive learning objective which gets its positive samples from data-augmented k-Nearest Neighbors search. We show that when built on top of recent self-supervised audio representations, this method can be applied iteratively and yield competitive SSE as evaluated on two tasks: query-by-example of random sequences of speech, and spoken term discovery. On both tasks our method pushes the state-of-the-art by a significant margin across 5 different languages. Finally, we establish a benchmark on a query-by-example task on the LibriSpeech dataset to monitor future improvements in the field.

📄 PDF Abstract BibTeX arXiv:2204.05148

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
SSE 설명 없음

Similar Papers 제목 키워드 기반

Unsupervised visualization of image datasets using contrastive learning

2022-10-18 · Jan Niklas Böhm, Philipp Berens, Dmitry Kobak

Visualization methods based on the nearest neighbor graph, such as t-SNE or UMAP, are widely used for visualizing high-dimensional data. Yet, these approaches only produce meaningful results if the nearest neighbors them…

Contrastive LearningData Augmentation

Supervised Contrastive Learning with Nearest Neighbor Search for Speech Emotion Recognition

2023-08-31 · Xuechen Wang, Shiwan Zhao, Yong Qin

Speech Emotion Recognition (SER) is a challenging task due to limited data and blurred boundaries of certain emotions. In this paper, we present a comprehensive approach to improve the SER performance throughout the mode…

Contrastive LearningEmotion RecognitionSpeech Emotion Recognition

On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors

2022-10-27 · Zaharah Bukhsh, Aaqib Saeed

Out-of-distribution (OOD) detection is concerned with identifying data points that do not belong to the same distribution as the model's training data. For the safe deployment of predictive models in a real-world environ…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Event DetectionOut-of-Distribution Detection+6

Promoting Semantic Connectivity: Dual Nearest Neighbors Contrastive Learning for Unsupervised Domain Generalization

2023-01-01 · CVPR 2023 1 · Yuchen Liu, Yaoming Wang, Yabo Chen, Wenrui Dai 외

Domain Generalization (DG) has achieved great success in generalizing knowledge from source domains to unseen target domains. However, current DG methods rely heavily on labeled source data, which are usually costly …

Contrastive LearningDomain GeneralizationLinear evaluation

k-Nearest Neighbors by Means of Sequence to Sequence Deep Neural Networks and Memory Networks

2018-04-27 · Yiming Xu, Diego Klabjan

k-Nearest Neighbors is one of the most fundamental but effective classification models. In this paper, we propose two families of models built on a sequence to sequence model and a memory network model to mimic the k-Nea…

General Classification