Language Model Verbalization for Automatic Speech Recognition

Source

• Evernote/Inbox/Language Model Verbalization for Automatic Speech Recognition.md

Summary

이 문서는 Hasim Sak 외 Google 연구진이 작성한 ‘Language Model Verbalization for Automatic Speech Recognition’ 논문의 메타데이터 링크입니다. 음성 인식(ASR) 시스템에서 언어 모델의 verbalization 기법을 다룬 것으로 보이나, 본문 내용 없이 PDF 링크와 검색 링크만 포함되어 있습니다.

Key Points

• Google 연구진의 ASR 관련 논문 메타데이터
• 주제: Language Model Verbalization for Automatic Speech Recognition
• 저자: Hasim Sak, Françoise Beaufays, Kaisuke Nakajima, Cyril Allauzen
• 실제 논문 내용은 PDF 링크를 통해 확인 필요

Related

• Accurate and Compact Large Vocabulary Speech Recognition on Mobile Devices

• Language Modeling Capitalization

• Speaker Adaptation of Context Dependent Deep Neural Networks

• Speech and Natural Language: Where Are We Now And Where Are We Headed

• AGC 및 다중 스타일 학습을 통한 소형 키워드 스포팅

• Deep Learning in Speech Synthesis (Google Research Talk)

• iVector-based Acoustic Data Selection

• State-based model slicing: A survey

• Target Language Adaptation of Discriminative Transfer Parsers

• Coordinated Multi-Device Presentations: Ambient-Audio Identification

• 오프라인 아랍어 손글씨 인식 기술 동향 (A Survey)

• Defunctionalized Interpreters for Call-by-Need Evaluation

• Breaking Out of Local Optima with Count Transforms and Model Recombination: A Study in Grammar Induction

• Token and Type Constraints for Cross-Lingual Part-of-Speech Tagging

• Scalable Decipherment for Machine Translation via Hash Sampling

• Improved Domain Adaptation for Statistical Machine Translation

• Affinity Weighted Embedding

• Anti-forensic resilient memory acquisition

• Behavioural reconfigurable and adaptive data reduction in body sensor networks

• Achieving anonymity via clustering

• Deep Learning via Semi-Supervised Embedding

• Summarization Through Submodularity and Dispersion

• From mixed-mode to multiple devices. Web surveys, smartphone surveys and apps

• A Semantic Matching Energy Function for Learning with Multi-relational Data

• DurIAN_4S: 말하기 데이터로부터 노래 합성 학습

• KamitaniLab DeepImageReconstruction 데이터 및 데모 코드

• Label Partitioning for Sublinear Ranking

• Accelerating defocus blur magnification

• Universal Dependency Annotation for Multilingual Parsing

• 내가 찾은 Deep Learning 공부 최단경로(?)

• 심층 신경망을 이용한 통계적 파라미터 음성 합성

• 음성 품질 지표의 배경 소음 및 네트워크 열화에 대한 강건성 비교 (VISQOL, PESQ, POLQA)

• Life of Pi 의 털 렌더링 기술 (Rendering Fur in Life of Pi)

• 영어 책 코퍼스 기반 시계열 구문 N-그램 데이터셋

• Acquisition of Open-Domain Classes via Intersective Semantics

• Recurrent Neural Networks for Voice Activity Detection

• 대규모 분산 음향 모델링 및 백오프 N-그램

• Facebook, 일부 딥러닝 도구 오픈소스화

• 3음만으로 음악을 식별하는 알고리즘 개발

• Learning Semantic Representations Of Objects And Their Parts

• SOINN (Self-Organizing Incremental Neural Network)

• Korea Globe Column (Document 20640)

• 심층 피처 합성 (Deep Feature Synthesis) 개요

• Learning Entangled Single-Sample Gaussians

• 모바일 음성 검색을 위한 Google 쿼리 스트림의 언어 모델링 경험적 탐색

• Efficient Estimation of Word Representations in Vector Space

• Optical design of a color-corrected 2.75 g visual loupe

• 신경망을 이용한 자기 학습 헬리콥터

• Acquisition of Noncontiguous Class Attributes from Web Search Queries

• Recent Books and Journals in Public Opinion, Survey Methods, and Survey Statistics

• Revenue Maximization with Nonexcludable Goods

• Coherent image selection using a fast approximation to the generalized traveling salesman problem

• Whole-page optimization and submodular welfare maximization with online bidders

• Distributed Large-scale Natural Graph Factorization

• A Local Algorithm for Finding Well-Connected Clusters

• Understanding Latency of Black-Box Service Workloads

• Measurement and modeling of eye-mouse behavior

• Two-stage Robust Network Design with Exponential Scenarios

• Scalability vs. Fault Tolerance in Aspen Trees

• 크리스토퍼 알렉산더의 『패턴 랭귀지(A Pattern Language)』

• Automated locality optimization based on the reuse distance of string operations

• 정치학 박사 학위의 광범위한 가치

• Energy and Cost Reduction in Localized Multisensory Systems through Application-Driven Compression

• Sok: The Evolution of Sybil Defense via Social Networks

• Convergence and approximation in potential games

• 모바일 네트워크 데이터를 활용한 도시 감지 연구 조사

• The Intervalgram: 대규모 커버송 인식을 위한 오디오 특징

• Our checklist for improving mobile websites

• 대리 지리적 연구 지역 식별을 위한 고급 정확 검정 통계

• Arrival and departure in Social Networks

• 공통 분석 및 MaxDiff 스케일링의 여론 조사 활용 잠재력

• Designing Markets for Daily Deals

• Latent Mixture of Discriminative Experts (LMDE)

• Conjoint Analysis in R: Individual-Level Utilities 및 Survey Mockups

• A Theoretical Examination of Practical Game Playing: Lookahead Search

• KDD 튜토리얼: 확장 가능한 혼합 멤버십 및 비모수 베이지안 모델 가이드

• How to approximate optimal auctions

• The Nested Chinese Restaurant Franchise Process: User Tracking and Document Modeling

• Multiprotocol Label Switching (MPLS)

• Hierarchical Geographical Modeling of User locations from Social Media Posts