RAMBLE: robust acoustic modeling for Brazilian learners of English

RAMBLE: robust acoustic modeling for Brazilian learners of English

The gains made by current deep-learning techniques have often come with the price tag of big data and where that data is not available, a new solution must be found. Such is the case for accented and noisy speech where large databases do not exist and data augmentation techniques, which are less tha...

Full description

Bibliographic Details
Main Author: Shulby, Christopher Dane
Other Authors: Aluisio, Sandra Maria
Format: Others
Language:en
Published: Biblioteca Digitais de Teses e Dissertações da USP 2018
Subjects:
Acoustic modeling
Aprendizado profundo
Computer vision
Convolutional neural networks
Deep learning
Máquinas de vetores de suporte
Modelagem acústica
Non-native phoneme recognition
Processamento de fala
Reconhecimento de fonemas não nativos
Redes neurais convolucionais
Speech processing
Statistical learning theory
Support vector machines
Teoria do aprendizado estatístico
Visão computacional
Online Access:http://www.teses.usp.br/teses/disponiveis/55/55134/tde-19102018-112733/

Internet

http://www.teses.usp.br/teses/disponiveis/55/55134/tde-19102018-112733/

Similar Items