Discriminative learning with latent articulatory variables

نویسندگان

  • Eric Fosler-Lussier
  • Preethi Jyothi
  • Joseph Keshet
  • Karen Livescu
  • Rohit Prabhavalkar
  • Hao Tang
چکیده

We review our recent work, which includes several disparate approaches and tasks, all with the goal of using latent articulatory structure while learning discriminatively.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Hybrid Deep Discriminative/Generative Models for Semi-Supervised Learning

Most methods in machine learning are described as either discriminative or generative. The former often attain higher predictive accuracy, while the latter are more strongly regularized and can deal with missing data. Here, we propose a new framework to combine a broad class of discriminative and generative models, interpolating between the two extremes with a multiconditional likelihood object...

متن کامل

Latent Variable Perceptron Algorithm for Structured Classification

We propose a perceptron-style algorithm for fast discriminative training of structured latent variable model, and analyzed its convergence properties. Our method extends the perceptron algorithm for the learning task with latent dependencies, which may not be captured by traditional models. It relies on Viterbi decoding over latent variables, combined with simple additive updates. Compared to e...

متن کامل

Accuracy of latent-variable estimation in Bayesian semi-supervised learning

Hierarchical probabilistic models, such as Gaussian mixture models, are widely used for unsupervised learning tasks. These models consist of observable and latent variables, which represent the observable data and the underlying data-generation process, respectively. Unsupervised learning tasks, such as cluster analysis, are regarded as estimations of latent variables based on the observable on...

متن کامل

Latent Discriminative Modeling for Lesion Detection in PET-CT Images

F-fluorodeoxyglucose positron emission tomography – computed tomography (FDG PET-CT) is now the best imaging technique to accurately stage non-small cell lung cancer (NSCLC). While an automated lesion detection system would help to reduce the time consumption and inter-observer differences in manual image interpretation, the accuracy of automated lesion detection is often limited by the intersu...

متن کامل

Deep Hybrid Models: Bridging Discriminative and Generative Approaches

Most methods in machine learning are described as either discriminative or generative. The former often attain higher predictive accuracy, while the latter are more strongly regularized and can deal with missing data. Here, we propose a new framework to combine a broad class of discriminative and generative models, interpolating between the two extremes with a multiconditional likelihood object...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013