Improved Neural Network Based Acoustic Modeling Leveraging Multi-task Learning and Ensemble Learning for Meeting Speech Recognition
碩士 === 國立臺灣師範大學 === 資訊工程學系 === 104 === This thesis sets out to explore the use of multi-task learning (MTL) and ensemble learning techniques for more accurate estimation of the parameters involved in neural network based acoustic models, so as to improve the accuracy of meeting speech recognition. O...
Main Authors: | Yang, Ming-Han, 楊明翰 |
---|---|
Other Authors: | Chen, Berlin |
Format: | Others |
Language: | zh-TW |
Published: |
2016
|
Online Access: | http://ndltd.ncl.edu.tw/handle/99106158778715235461 |
Similar Items
-
Ensemble Learning of Hybrid Acoustic Features for Speech Emotion Recognition
by: Kudakwashe Zvarevashe, et al.
Published: (2020-03-01) -
Deep Neural Networks and Ensemble Learning with Application to Speech Emotion Recognition
by: Po-Wei Hsiao, et al.
Published: (2018) -
A Multi-Task Learning Approach to Hate Speech Detection Leveraging Sentiment Analysis
by: Flor Miriam Plaza-Del-Arco, et al.
Published: (2021-01-01) -
Classification of Alzheimer’s Disease Leveraging Multi-task Machine Learning Analysis of Speech and Eye-Movement Data
by: Barral, O., et al.
Published: (2021) -
Classification of Alzheimer’s Disease Leveraging Multi-task Machine Learning Analysis of Speech and Eye-Movement Data
by: Hyeju Jang, et al.
Published: (2021-09-01)