TAILIEUCHUNG - Báo cáo khoa học: "Using Speech to Reply to SMS Messages While Driving: An In-Car Simulator User Study"

Speech recognition affords automobile drivers a hands-free, eyes-free method of replying to Short Message Service (SMS) text messages. Although a voice search approach based on template matching has been shown to be more robust to the challenging acoustic environment of automobiles than using dictation, users may have difficulties verifying whether SMS response templates match their intended meaning, especially while driving. Using a high-fidelity driving simulator, we compared dictation for SMS replies versus voice search in increasingly difficult driving conditions. . | Using Speech to Reply to SMS Messages While Driving An In-Car Simulator User Study Yun-Cheng Ju Tim Paek Microsoft Research Redmond WA USA yuncj timpaek @ Abstract Speech recognition affords automobile drivers a hands-free eyes-free method of replying to Short Message Service SMS text messages. Although a voice search approach based on template matching has been shown to be more robust to the challenging acoustic environment of automobiles than using dictation users may have difficulties verifying whether SMS response templates match their intended meaning especially while driving. Using a high-fidelity driving simulator we compared dictation for SMS replies versus voice search in increasingly difficult driving conditions. Although the two approaches did not differ in terms of driving performance measures users made about six times more errors on average using dictation than voice search. 1 Introduction Users love Short Message Service SMS text messaging so much so that 3 trillion SMS messages are expected to have been sent in 2009 alone Stross 2008 . Because research has shown that SMS messaging while driving results in 35 slower reaction time than being intoxicated Reed Robbins 2008 campaigns have been launched by states governments and even cell phone carriers to discourage and ban SMS messaging while driving DOT 2009 . Yet automobile manufacturers have started to offer infotainment systems such as the Ford Sync which feature the ability to listen to incoming SMS messages using text-to-speech TTS . Automatic speech recognition ASR affords users a hands-free eyes-free method of replying to SMS messages. However to date manufacturers have not established a safe and reliable method of leveraging ASR though some researchers have begun to explore techniques. In previous research Ju Paek 2009 we examined three ASR approaches to replying to SMS messages dictation using a language model trained on SMS responses canned responses using a probabilistic .

• Báo cáo khoa học
• Using Speech
• Reply to SMS Messages While Driving
• An In Car Simulator User Study
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Using Chunk Based Partial Parsing of Spontaneous Speech in Unrestricted Domains
• Reducing Word Error Rate
• Speech Recognition
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Common errors of reported speech
• common errors in using reported speech
• Errors of reported speech
• Báo cáo nghiên cứu khoa học
• Nghiên cứu khoa học
• Windows Phone Speech
• Lock Screen Notifications
• Enabling Speech Synthesis
• Controlling Applications
• Fortune Teller Program
• Voice Command Definition
• Journal of Science and Technology
• Blind multi channel speech separation
• Spatial estimation in two speaker environments
• Expense of permutation ambiguity
• Mixture of two speech signals
• Neural network based tonal feature
• Vietnamese speech recognition
• Multi space distribution model
• Multi Space Distribution Hidden Markov Model
• Vietnamese Automatic Speech recognition
• Text to speech
• Speech synthesis
• Deep neural network
• Hidden Markov model
• TTS systems
• Using Conditional Random Fields
• Sentence Boundary
• Detection In Speech
• Using Conditional Random
• Fields to Predict Pitch
• Accents in Conversational Speech
• Knowledge acquisition
• constrained speech system using WoZ
• Laila Dybkjver
• scientific reports
• model language
• process natural language
• Blind speech separation
• Convolutive mixtures using negentropy maximization
• Re coloration filters
• Blind signal separation
• Independent component analysis
• The robust ASR using uncertainty of observation techniques
• The robust ASR
• The robustness of ASR however
• Automatic speech recognition
• Speech perception
• Scale invariant Feature Transform
• Spectrogram images
• Speech classification
• TMW database
• báo cáo hóa học
• công trình nghiên cứu về hóa học
• tài liệu về hóa học
• cách trình bày báo cáo
• Fast and Robust
• Part of Speech Tagging
• Dynamic Model Selection
• A Speech based Just in Time Retrieval System
• Semantic Search
• Andrei Popescu Belis
• Guessing Parts of Speech
• Unknown Words
• Global Information
• Integration of Speech
• to Computer Assisted Translation
• Finite State Automata
• A Limited Domain English to Japanese
• Medical Speech Translator Built
• REGULUS 2
• A Method for Correcting Errors
• the Statistical Features of Character Co occurrence
• Predicting Part of Speech Information
• Statistical Methods
• a Network of Linear Separators
• Long Papers
• Analysis System of Speech Acts
• Discourse Structures
• Maximum Entropy Model
• A Part of Speech Estimation Method
• Japanese Unknown Words
• a Statistical Model of Morphology and Context