paper-with-me

홈 › Papers

Semi-supervised Learning with Sparse Autoencoders in Phone Classification

2016-10-03 · Akash Kumar Dhaka, Giampiero Salvi

We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by supervised fine tuning, our method takes advantage of both unlabelled and labelled data simultaneously through mini- batch stochastic gradient descent. We tested the method with varying proportions of labelled vs unlabelled observations in frame-based phoneme classification on the TIMIT database. Our experiments show that the method outperforms standard supervised training for an equal amount of labelled data and provides competitive error rates compared to state-of-the-art graph-based semi-supervised learning techniques.

📄 PDF Abstract BibTeX arXiv:1610.00520

Code (0)

등록된 구현이 없습니다.

Tasks

Acoustic ModellingAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)ClassificationGeneral Classificationspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Augmenting Variational Autoencoders with Sparse Labels: A Unified Framework for Unsupervised, Semi-(un)supervised, and Supervised Learning

2019-08-08 · Felix Berkhahn, Richard Keys, Wajih Ouertani, Nikhil Shetty 외

We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsuperv…

ClassificationDecoderGeneral Classification

Learning Consistent Deep Generative Models from Sparse Data via Prediction Constraints

2020-12-12 · Gabriel Hope, Madina Abdrakhmanova, Xiaoyin Chen, Michael C. Hughes 외

We develop a new framework for learning variational autoencoders and other deep generative models that balances generative and discriminative goals. Our framework optimizes model parameters to maximize a variational lowe…

General Classificationimage-classificationImage Classification

vONTSS: vMF based semi-supervised neural topic modeling with optimal transport

2023-07-03 · Weijie Xu, Xiaoyu Jiang, Srinivasan H. Sengamedu, Francis Iannacci 외

Recently, Neural Topic Models (NTM), inspired by variational autoencoders, have attracted a lot of research interest; however, these methods have limited applications in the real world due to the challenge of incorporati…

ClassificationDiversitytext-classificationText Classification+2

Semi-supervised source localization in reverberant environments with deep generative modeling

2021-01-26 · Michael J. Bianco, Sharon Gannot, Efren Fernandez-Grande, Peter Gerstoft

We propose a semi-supervised approach to acoustic source localization in reverberant environments based on deep generative modeling. Localization in reverberant environments remains an open challenge. Even with large dat…

Learning Consistent Deep Generative Models from Sparsely Labeled Data

2021-11-22 · pproximateinference AABI Symposium 2022 2 · Gabriel Hope, Madina Abdrakhmanova, Xiaoyin Chen, Michael C Hughes 외

We consider training deep generative models toward two simultaneous goals: discriminative classification and generative modeling using an explicit likelihood. While variational autoencoders (VAEs) offer a promising solut…

image-classificationImage Classification