For Evaluating Dialog Error Conditions Based on Acoustic Information

Slides:



Advertisements
Similar presentations
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Advertisements

Speed dating Classification What you should know about dating Stephen Cohen Rajesh Ranganath Te Thamrongrattanarit.
Slides from: Doug Gray, David Poole
CPSC 502, Lecture 15Slide 1 Introduction to Artificial Intelligence (AI) Computer Science cpsc502, Lecture 15 Nov, 1, 2011 Slide credit: C. Conati, S.
Towards Twitter Context Summarization with User Influence Models Yi Chang et al. WSDM 2013 Hyewon Lim 21 June 2013.
Using the Crosscutting Concepts As conceptual tools when meeting an unfamiliar problem or phenomenon.
ASSESSING SEARCH TERM STRENGTH IN SPOKEN TERM DETECTION Amir Harati and Joseph Picone Institute for Signal and Information Processing, Temple University.
About ISoft … What is Decision Tree? Alice Process … Conclusions Outline.
Speaker Adaptation for Vowel Classification
Modeling the Cost of Misunderstandings in the CMU Communicator System Dan BohusAlex Rudnicky School of Computer Science, Carnegie Mellon University, Pittsburgh,
Feature vs. Model Based Vocal Tract Length Normalization for a Speech Recognition-based Interactive Toy Jacky CHAU Department of Computer Science and Engineering.
Data Mining CS 341, Spring 2007 Lecture 4: Data Mining Techniques (I)
GUHA method in Data Mining Esko Turunen Tampere University of Technology Tampere, Finland.
Toshiba Update 04/09/2006 Data-Driven Prosody and Voice Quality Generation for Emotional Speech Zeynep Inanoglu & Steve Young Machine Intelligence Lab.
EE513 Audio Signals and Systems Statistical Pattern Classification Kevin D. Donohue Electrical and Computer Engineering University of Kentucky.
SoundSense: Scalable Sound Sensing for People-Centric Application on Mobile Phones Hon Lu, Wei Pan, Nocholas D. lane, Tanzeem Choudhury and Andrew T. Campbell.
Drones Collecting Cell Phone Data in LA AdNear had already been using methods.
Machine Learning1 Machine Learning: Summary Greg Grudic CSCI-4830.
Statistics Chapter 9. Statistics Statistics, the collection, tabulation, analysis, interpretation, and presentation of numerical data, provide a viable.
This work is supported by the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior National Business Center contract number.
Simulation is the process of studying the behavior of a real system by using a model that replicates the behavior of the system under different scenarios.
1 Value of information – SITEX Data analysis Shubha Kadambe (310) Information Sciences Laboratory HRL Labs 3011 Malibu Canyon.
Number Sense Disambiguation Stuart Moore Supervised by: Anna Korhonen (Computer Lab)‏ Sabine Buchholz (Toshiba CRL)‏
Intelligent DataBase System Lab, NCKU, Taiwan Josh Jia-Ching Ying, Eric Hsueh-Chan Lu, Wen-Ning Kuo and Vincent S. Tseng Institute of Computer Science.
Speech Lab, ECE, State University of New York at Binghamton  Classification accuracies of neural network (left) and MXL (right) classifiers with various.
CSE 5331/7331 F'07© Prentice Hall1 CSE 5331/7331 Fall 2007 Regression Margaret H. Dunham Department of Computer Science and Engineering Southern Methodist.
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
The Use of Technology in Psychology fMRI’s. The use of Technology in Psychology Modern psychology is now utilized in neuropsychology due to the fact it.
Predicting Children’s Reading Ability using Evaluator-Informed Features Matthew Black, Joseph Tepperman, Sungbok Lee, and Shrikanth Narayanan Signal Analysis.
A Bayesian Network Classifier for Word-level Reading Assessment Joseph Tepperman 1, Matthew Black 1, Patti Price 2, Sungbok Lee 1, Abe Kazemzadeh 1, Matteo.
A Text-free Approach to Assessing Nonnative Intonation Joseph Tepperman, Abe Kazemzadeh, and Shrikanth Narayanan Signal Analysis and Interpretation Laboratory,
Introduction to Machine Learning, its potential usage in network area,
Experience Report: System Log Analysis for Anomaly Detection
Intelligent HIV/AIDS FAQ Retrieval System Using Neural Networks
Sentiment analysis algorithms and applications: A survey
SENSOR FUSION LAB RESEARCH ACTIVITIES PART I : DATA FUSION AND DISTRIBUTED SIGNAL PROCESSING IN SENSOR NETWORKS Sensor Fusion Lab, Department of Electrical.
Chapter 6. Data Collection in a Wizard-of-Oz Experiment in Reinforcement Learning for Adaptive Dialogue Systems by: Rieser & Lemon. Course: Autonomous.
Computer Science and Engineering, Seoul National University
Prepared by: Mahmoud Rafeek Al-Farra
Instance Based Learning
Dean Luo, Wentao Gu, Ruxin Luo and Lixin Wang
Towards Emotion Prediction in Spoken Tutoring Dialogues
Tracking parameter optimization
Spoken Dialogue Systems
Multimedia Information Retrieval
Hidden Markov Models Part 2: Algorithms
A Similarity Retrieval System for Multimodal Functional Brain Images
Spoken Dialogue Systems
General Aspects of Learning
Disambiguation Algorithm for People Search on the Web
iSRD Spam Review Detection with Imbalanced Data Distributions
Computer Vision Chapter 4
EE513 Audio Signals and Systems
CS548 Fall 2018 Model and Regression Trees
Course Lab Introduction to IBM Watson Analytics
Ying Dai Faculty of software and information science,
MACHINE LEARNING TECHNIQUES IN IMAGE PROCESSING
MACHINE LEARNING TECHNIQUES IN IMAGE PROCESSING
John H.L. Hansen & Taufiq Al Babba Hasan
Machine Learning for Visual Scene Classification with EEG Data
NAACL-HLT 2010 June 5, 2010 Jee Eun Kim (HUFS) & Kong Joo Lee (CNU)
Anthor: Andreas Tsiartas, Prasanta Kumar Ghosh,
Actively Learning Ontology Matching via User Interaction
Geography.
Measurements & Error Analysis
August 8, 2006 Danny Budik, Itamar Elhanany Machine Intelligence Lab
WSExpress: A QoS-Aware Search Engine for Web Services
General Aspects of Learning
Yingze Wang and Shi-Kuo Chang University of Pittsburgh
A Deep Reinforcement Learning Approach to Traffic Management
Presentation transcript:

For Evaluating Dialog Error Conditions Based on Acoustic Information Using Model Trees For Evaluating Dialog Error Conditions Based on Acoustic Information Goal Use model trees for evaluating user utterances for response to system error. Input: acoustic features from user’s speech signal. Output: a measure representing user activation. Develop an online, objective, human-centered evaluation metric for spoken dialog systems. Abe Kazemzadeh, Sungbok Lee, and Shrikanth Narayanan Computer Science, Electrical Engineering, and Linguistics SAIL Lab @ Viterbi School of Engineering University of Southern California Motivation Errors are a prevalent phenomenon in spoken dialog systems. Evaluate and optimize of dialog systems. Obtain feedback from user behavior. Synthesize low-level features into one, real-valued measurement of a user’s activation. Results Histograms of the model tree output for the whole corpus (histogram 1), for error responses (histogram 2), and for non-error responses (histogram 3). Lower left plot shows the precision and recall. Data Communicator Travel Planning Systems, June 2000 recordings. Annotated to describe the way that users become aware of and react to errors. 141 dialogs, 2586 utterances. Model Trees Machine learning technique, similar to decision trees and model trees. Outputs a continuous, real-valued number based on a linear regression model for each leaf node. Best correlation with user surveys occurred when model tree output sums were normalized for dialog length and when only the highest 30% were considered. Methodology Evaluation Metric Correlation With: Tag Data ModelTree Output It was easy to get info I wanted .412 .389 I found it easy to understand what the sys. Said .035 .092 I knew what I could say or do at each point in the dial. .269 .311 The system worked the way I expected it to .365 .498 I would like to use the system regularly .332 .409 Feature extraction: Train by using annotated data: if there is an error response, set model tree target to 1, else, 0. Analysis Conclusion Overall ability to pick out error responses is 65% precision, 63% recall. The model tree approach allows for a threshold that can shift preferents toward precision or recall. Correlation between model tree analysis and survey results was moderate. Different questions showed different levels of correlation. Model tree output can be interpreted as an indicator of user state and can show a dialog activation landscape which can be used in user emotion tracking, e.g., to identify dialog hotspots. Future work will aim to further this study by: Testing other methods of synthesizing lower level features, in particular, Bayesian networks Examining other corpora. Currently analyzing All My Sons radio play. Example