Bayesian adaptation and combination of deep models for automatic speech recognition
الملخص
The objective of the proposed research is to deploy a Bayesian adaptation and combination framework for deep model based automatic speech recognition systems to combat the degradation of the recognition accuracy, which is typically observed under potential mismatched conditions between training and testing. This dissertation addresses the problem in three directions. The first direction is to perform Bayesian adaptation directly on the discriminative deep neural network models. Maximum a posteriori estimation and multi-task learning techniques are employed in the manner of regularization in the deep neural network updating formula. In the second direction, deep neural network is cast into a generative model to better leverage Bayesian techniques. Classic structured maximum a posteriori adaption is adopted by using bottleneck features derived from deep neural networks. In the third direction, a hierarchical Bayesian system combination technique is employed to further enhance the adaptation performance by leveraging the complementarity of the discriminative and generative adaptive models.
الكلمات المفتاحية
غير متوفر
التخصصات
رسائل وأطاريح مشابهة
- Speaker adaptation of deep neural network acoustic models using Gaussian mixture model framework in automatic speech recognition systems Natalia Tomashenko · 2017
- Streaming Automatic Speech Recognition with Hybrid Architectures and Deep Neural Network Models Javier Jorge Cano · Universitat Politècnica de València · 2022
- Towards Probabilistic Generative Models for Socially Intelligent Robots Xavier Alameda-Pineda · 2020
- Single-Channel Speech Enhancement Based on Deep Neural Networks Zhiheng Ouyang · Concordia University · 2019
- Automatic speech recognition and machine translation with deep neural networks for open educational resources, parliamentary contents and broadcast media Gonzalo Vicente Garcés Díaz-Munío · Universitat Politècnica de València · 2024
- Study of transfer learning and domain adaptation for language modeling in end-to-end speech recognition 卓 龔 · 2023
