Accurate and Compact Large Vocabulary Speech Recognition on Mobile Devices
Source
Evernote/Inbox/Accurate and Compact Large Vocabulary Speech Recognition on Mobile Devices.md
Summary
이 문서는 모바일 기기에서 정확하고 컴팩트한 대규모 어휘 음성 인식 기술을 다룬 Google 연구 논문(저자: Xin Lei 외)의 메타데이터 링크입니다.
Key Points
- 모바일 환경에서의 대규모 어휘 음성 인식(Speech Recognition) 연구
- 정확성과 모델의 컴팩트함(Compactness)을 동시에 추구
- 저자: Xin Lei, Andrew Senior, Alexander Gruenstein, Jeffrey Sorensen
Related
-
Language Model Verbalization for Automatic Speech Recognition
-
Robust and accurate mobile visual localization and its applications
-
Speech and Natural Language: Where Are We Now And Where Are We Headed
-
Speaker Adaptation of Context Dependent Deep Neural Networks
-
Coordinated Multi-Device Presentations: Ambient-Audio Identification
-
Target Language Adaptation of Discriminative Transfer Parsers
-
Behavioural reconfigurable and adaptive data reduction in body sensor networks
-
From mixed-mode to multiple devices. Web surveys, smartphone surveys and apps
-
Improved Domain Adaptation for Statistical Machine Translation
-
Scalable Decipherment for Machine Translation via Hash Sampling
-
Efficient Estimation of Word Representations in Vector Space
-
Token and Type Constraints for Cross-Lingual Part-of-Speech Tagging
-
Continuous Birdsong Recognition Using Gaussian Mixture Modeling of Image Shape Features
-
Fast, Accurate Detection of 100,000 Object Classes on a Single Machine (Technical Supplement)
-
Enlisting the Ghost: Modeling Empty Categories for Machine Translation
-
A Semantic Matching Energy Function for Learning with Multi-relational Data
-
Wireless Networks Design in the Era of Deep Learning Model-Based, AI-Based, or Both