iVector-based Acoustic Data Selection
Source
Evernote/IFTTT Feedly/iVector-based Acoustic Data Selection.md
Summary
Olivier Siohan과 Michiel Bacchiani가 작성한 Google 연구 논문으로, iVector를 활용한 음향 데이터 선택 기법을 다룹니다.
Key Points
- 저자: Olivier Siohan, Michiel Bacchiani (Google)
- 주제: iVector 기반 음향 데이터 선택 방법론
- 출처: Google Research Publications (2013년 9월)
Related
-
Accurate and Compact Large Vocabulary Speech Recognition on Mobile Devices
-
Coordinated Multi-Device Presentations: Ambient-Audio Identification
-
Language Model Verbalization for Automatic Speech Recognition
-
Speech and Natural Language: Where Are We Now And Where Are We Headed
-
Target Language Adaptation of Discriminative Transfer Parsers
-
Speaker Adaptation of Context Dependent Deep Neural Networks
-
Improved Domain Adaptation for Statistical Machine Translation
-
Efficient Estimation of Word Representations in Vector Space
-
Scalable Decipherment for Machine Translation via Hash Sampling
-
Token and Type Constraints for Cross-Lingual Part-of-Speech Tagging
-
Behavioural reconfigurable and adaptive data reduction in body sensor networks
-
Near-duplicate video retrieval: Current research and future trends
-
Feature Ensemble Plus Sample Selection: Domain Adaptation for Sentiment Classification
-
An Unsupervised Feature Selection Framework for Social Media Data
-
Robust and accurate mobile visual localization and its applications
-
지오태그 이미지로부터 장면 위치 식별 (Identification of scene locations from geotagged images)
-
From mixed-mode to multiple devices. Web surveys, smartphone surveys and apps
-
A Semantic Matching Energy Function for Learning with Multi-relational Data
-
Continuous Birdsong Recognition Using Gaussian Mixture Modeling of Image Shape Features
-
Eureka: Edge-Based Discovery of Training Data for Machine Learning
-
Smooth Nonnegative Matrix Factorization for Unsupervised Audiovisual Document Structuring
-
실내 이동 객체를 위한 거리 기반 조인 (Distance-Aware Join for Indoor Moving Objects)