English
Related papers

Related papers: Weakly Supervised Multi-Embeddings Learning of Aco…

200 papers

Embedding audio signal segments into vectors with fixed dimensionality is attractive because all following processing will be easier and more efficient, for example modeling, classifying or indexing. Audio Word2Vec previously proposed was…

Computation and Language · Computer Science 2018-11-08 Sung-Feng Huang , Yi-Chen Chen , Hung-yi Lee , Lin-shan Lee

We present a novel approach to multilingual audio-visual speech recognition tasks by introducing a single model on a multilingual dataset. Motivated by a human cognitive system where humans can intuitively distinguish different languages…

Multimedia · Computer Science 2023-10-24 Joanna Hong , Se Jin Park , Yong Man Ro

Supervised learning for single-channel speech enhancement requires carefully labeled training examples where the noisy mixture is input into the network and the network is trained to produce an output close to the ideal target. To relax the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-19 Yu-Che Wang , Shrikant Venkataramani , Paris Smaragdis

This paper presents a unified model to perform language and speaker recognition simultaneously and altogether. The model is based on a multi-task recurrent neural network where the output of one task is fed as the input of the other,…

Sound · Computer Science 2017-05-24 Lantian Li , Zhiyuan Tang , Dong Wang , Andrew Abel , Yang Feng , Shiyue Zhang

Self-supervised learning methods such as wav2vec 2.0 have shown promising results in learning speech representations from unlabelled and untranscribed speech data that are useful for speech recognition. Since these representations are…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-22 Shehzeen Hussain , Van Nguyen , Shuhua Zhang , Erik Visser

This paper introduces contrastive siamese (c-siam) network, an architecture for leveraging unlabeled acoustic data in speech recognition. c-siam is the first network that extracts high-level linguistic information from speech by matching…

Machine Learning · Computer Science 2022-05-30 Soheil Khorram , Jaeyoung Kim , Anshuman Tripathi , Han Lu , Qian Zhang , Hasim Sak

Existing weakly supervised semantic segmentation (WSSS) methods usually utilize the results of pre-trained saliency detection (SD) models without explicitly modeling the connections between the two tasks, which is not the most efficient…

Computer Vision and Pattern Recognition · Computer Science 2019-09-11 Yu Zeng , Yunzhi Zhuge , Huchuan Lu , Lihe Zhang

Neural networks have been successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are more difficult to train successfully for semi-supervised…

Machine Learning · Computer Science 2021-09-13 Attaullah Sahito , Eibe Frank , Bernhard Pfahringer

Self-supervised learning approaches have lately achieved great success on a broad spectrum of machine learning problems. In the field of speech processing, one of the most successful recent self-supervised models is wav2vec 2.0. In this…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-10 Marie Kunešová , Zbyněk Zajíc

Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically…

Computation and Language · Computer Science 2020-06-26 Yushi Hu , Shane Settle , Karen Livescu

Speech enhancement (SE) and neural vocoding are traditionally viewed as separate tasks. In this work, we observe them under a common thread: the rank behavior of these processes. This observation prompts two key questions: \textit{Can a…

Sound · Computer Science 2025-01-24 Andong Li , Zhihang Sun , Fengyuan Hao , Xiaodong Li , Chengshi Zheng

This paper have two parts. In the first part we discuss word embeddings. We discuss the need for them, some of the methods to create them, and some of their interesting properties. We also compare them to image embeddings and see how word…

Machine Learning · Computer Science 2016-10-27 Amit Mandelbaum , Adi Shalev

Image-language matching tasks have recently attracted a lot of attention in the computer vision field. These tasks include image-sentence matching, i.e., given an image query, retrieving relevant sentences and vice versa, and region-phrase…

Computer Vision and Pattern Recognition · Computer Science 2018-05-03 Liwei Wang , Yin Li , Jing Huang , Svetlana Lazebnik

While neural networks have been employed to handle several different text-to-speech tasks, ours is the first system to use neural networks throughout, for both linguistic and acoustic processing. We divide the text-to-speech task into three…

Neural and Evolutionary Computing · Computer Science 2016-11-17 Orhan Karaali , Gerald Corrigan , Noel Massey , Corey Miller , Otto Schnurr , Andrew Mackie

Neural network based models have achieved impressive results on various specific tasks. However, in previous works, most models are learned separately based on single-task supervised objectives, which often suffer from insufficient training…

Computation and Language · Computer Science 2016-09-26 Pengfei Liu , Xipeng Qiu , Xuanjing Huang

Semantic Pattern Similarity is an interesting, though not often encountered NLP task where two sentences are compared not by their specific meaning, but by their more abstract semantic pattern (e.g., preposition or frame). We utilize…

Computation and Language · Computer Science 2018-12-18 Yassine Benajiba , Jin Sun , Yong Zhang , Longquan Jiang , Zhiliang Weng , Or Biran

Many supervised learning tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation. Two dual tasks have…

Machine Learning · Computer Science 2017-07-04 Yingce Xia , Tao Qin , Wei Chen , Jiang Bian , Nenghai Yu , Tie-Yan Liu

We consider the statistical problem of learning common source of variability in data which are synchronously captured by multiple sensors, and demonstrate that Siamese neural networks can be naturally applied to this problem. This approach…

Machine Learning · Statistics 2016-05-12 Uri Shaham , Roy Lederman

With the increase in the number of open repositories and discussion forums, the use of natural language for semantic code search has become increasingly common. The accuracy of the results returned by such systems, however, can be low due…

Software Engineering · Computer Science 2020-11-03 Raunak Sinha , Utkarsh Desai , Srikanth Tamilselvam , Senthil Mani

Although there are more than 6,500 languages in the world, the pronunciations of many phonemes sound similar across the languages. When people learn a foreign language, their pronunciation often reflects their native language's…

Computation and Language · Computer Science 2020-06-25 Younggun Lee , Suwon Shon , Taesu Kim