Sciweavers

2047 search results - page 317 / 410
» The limits of speech recognition
Sort
View
ICASSP
2008
IEEE
14 years 3 months ago
A new mutual information measure for independent component alalysis
Independent component analysis (ICA) is a popular approach for blind source separation (BSS). In this study, we develop a new mutual information measure for BSS and unsupervised l...
Jen-Tzung Chien, Hsin-Lung Hsieh, Sadaoki Furui
ICASSP
2008
IEEE
14 years 3 months ago
Learning with noisy supervision for Spoken Language Understanding
Data-driven Spoken Language Understanding (SLU) systems need semantically annotated data which are expensive, time consuming and prone to human errors. Active learning has been su...
Christian Raymond, G. Riccardfi
ICASSP
2008
IEEE
14 years 3 months ago
Unsupervised optimal phoneme segmentation: Objectives, algorithm and comparisons
Phoneme segmentation is a fundamental problem in many speech recognition and synthesis studies. Unsupervised phoneme segmentation assumes no knowledge on linguistic contents and a...
Yu Qiao, Naoya Shimomura, Nobuaki Minematsu
ICASSP
2008
IEEE
14 years 3 months ago
Optimizing the acoustic modeling from an unbalanced bi-lingual corpus
Phoneme set clustering of accurate modeling is important in the task of multilingual speech recognition, especially when each of the available language training corpora is mismatc...
Dau-cheng Lyu, Ren-yuan Lyu
ROMAN
2007
IEEE
111views Robotics» more  ROMAN 2007»
14 years 3 months ago
Understanding Rules in Human-Robot Instructions
— This paper presents an overview of the systematic creation of a human-robot instruction system from a multi-modal corpus. The corpus has been collected from human-to-human card...
Joerg C. Wolf, Guido Bugmann