English
Related papers

Related papers: Burst2Vec: An Adversarial Multi-Task Approach for …

200 papers

While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self-supervised…

Machine Learning · Computer Science 2022-10-27 Alexei Baevski , Wei-Ning Hsu , Qiantong Xu , Arun Babu , Jiatao Gu , Michael Auli

We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to a multi-modal two-stream model, pro-cessing…

Computer Vision and Pattern Recognition · Computer Science 2019-08-07 Jiasen Lu , Dhruv Batra , Devi Parikh , Stefan Lee

While Wav2Vec 2.0 has been proposed for speech recognition (ASR), it can also be used for speech emotion recognition (SER); its performance can be significantly improved using different fine-tuning strategies. Two baseline methods, vanilla…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-22 Li-Wei Chen , Alexander Rudnicky

Neural latent variable models enable the discovery of interesting structure in speech audio data. This paper presents a comparison of two different approaches which are broadly based on predicting future time-steps or auto-encoding the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-28 Henry Zhou , Alexei Baevski , Michael Auli

Emotion Recognition in Conversations (ERC) is crucial in developing sympathetic human-machine interaction. In conversational videos, emotion can be present in multiple modalities, i.e., audio, video, and transcript. However, due to the…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Vishal Chudasama , Purbayan Kar , Ashish Gudmalwar , Nirmesh Shah , Pankaj Wasnik , Naoyuki Onoe

Deep speech classification tasks, mainly including keyword spotting and speaker verification, play a crucial role in speech-based human-computer interaction. Recently, the security of these technologies has been demonstrated to be…

Sound · Computer Science 2024-09-09 Wenhan Yao , Zedong XingXiarun Chen , Jia Liu , yongqiang He , Weiping Wen

Automated prediction of valence, one key feature of a person's emotional state, from individuals' personal narratives may provide crucial information for mental healthcare (e.g. early diagnosis of mental diseases, supervision of disease…

Computation and Language · Computer Science 2019-12-03 Aniruddha Tammewar , Alessandra Cervone , Eva-Maria Messner , Giuseppe Riccardi

This paper investigates the application of voice activity projection (VAP), a predictive turn-taking model for spoken dialogue, on multilingual data, encompassing English, Mandarin, and Japanese. The VAP model continuously predicts the…

Computation and Language · Computer Science 2024-03-18 Koji Inoue , Bing'er Jiang , Erik Ekstedt , Tatsuya Kawahara , Gabriel Skantze

Speech Emotion Recognition (SER) plays a pivotal role in enhancing human-computer interaction by enabling a deeper understanding of emotional states across a wide range of applications, contributing to more empathetic and effective…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-25 Amirali Soltani Tehrani , Niloufar Faridani , Ramin Toosi

Emotion Recognition in Conversation (ERC) plays an important role in driving the development of human-machine interaction. Emotions can exist in multiple modalities, and multimodal ERC mainly faces two problems: (1) the noise problem in the…

Computation and Language · Computer Science 2023-10-10 Shihao Zou , Xianying Huang , Xudong Shen

Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…

Machine Learning · Computer Science 2019-02-15 Yossi Adi , Neil Zeghidour , Ronan Collobert , Nicolas Usunier , Vitaliy Liptchinsky , Gabriel Synnaeve

This paper describes our submission to ICASSP 2022 Multi-channel Multi-party Meeting Transcription (M2MeT) Challenge. For Track 1, we propose several approaches to empower the clustering-based speaker diarization system to handle overlapped…

Sound · Computer Science 2022-02-11 Chen Shen , Yi Liu , Wenzhi Fan , Bin Wang , Shixue Wen , Yao Tian , Jun Zhang , Jingsheng Yang , Zejun Ma

Emotion recognition is a critical task in human-computer interaction, enabling more intuitive and responsive systems. This study presents a multimodal emotion recognition system that combines low-level information from audio and text,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-23 Shamin Bin Habib Avro , Taieba Taher , Nursadul Mamun

Audio Word2Vec offers vector representations of fixed dimensionality for variable-length audio segments using Sequence-to-sequence Autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of…

Computation and Language · Computer Science 2018-02-20 Chia-Hao Shen , Janet Y. Sung , Hung-Yi Lee

Unsupervised representation learning has shown remarkable achievement by reducing the performance gap with supervised feature learning, especially in the image domain. In this study, to extend the technique of unsupervised learning to the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-23 Jangho Lee , Jaihyun Koh , Sungroh Yoon

This project intends to study the image representation based on attention mechanism and multimodal data. By adding multiple pattern layers to the attribute model, the semantic and hidden layers of image content are integrated. The word…

Computation and Language · Computer Science 2024-06-14 Dan Sun , Yaxin Liang , Yining Yang , Yuhan Ma , Qishi Zhan , Erdi Gao

Existing fake audio detection systems perform well in in-domain testing, but still face many challenges in out-of-domain testing. This is due to the mismatch between the training and test data, as well as the poor generalizability of…

Sound · Computer Science 2023-05-24 Chenglong Wang , Jiangyan Yi , Jianhua Tao , Chuyuan Zhang , Shuai Zhang , Xun Chen

Emotion recognition in conversations is essential for ensuring advanced human-machine interactions. However, creating robust and accurate emotion recognition systems in real life is challenging, mainly due to the scarcity of emotion…

Computation and Language · Computer Science 2023-08-30 Théo Deschamps-Berger , Lori Lamel , Laurence Devillers

In this paper, we present our solution for the Second Multimodal Emotion Recognition Challenge Track 1(MER2024-SEMI). To enhance the accuracy and generalization performance of emotion recognition, we propose several methods for Multimodal…

Computer Vision and Pattern Recognition · Computer Science 2024-09-12 Anbin QI , Zhongliang Liu , Xinyong Zhou , Jinba Xiao , Fengrun Zhang , Qi Gan , Ming Tao , Gaozheng Zhang , Lu Zhang

Detecting humor is a challenging task since words might share multiple valences and, depending on the context, the same words can be even used in offensive expressions. Neural network architectures based on Transformer obtain…

Computation and Language · Computer Science 2021-04-14 Răzvan-Alexandru Smădu , Dumitru-Clementin Cercel , Mihai Dascalu