- Sundermann, Hoge, Fingscheidt: ..Applying VTLN to Residuals
- D. Suendermann, J. Liscombe, R. Pieraccini SpeechCycle Labs, New York, USA
- Technology and Corpora for Speech to Speech Translation http://www.tc-star.org
- Lombard Speech Recognition: A Comparative Study , P. Fousek1
- An Automatic Segmentation and Mapping Approach for Voice Conversion Parameter Training
- FROM RULE-BASED TO STATISTICAL GRAMMARS: CONTINUOUS IMPROVEMENT OF LARGE-SCALE SPOKEN DIALOG SYSTEMS
- A Handsome Set of Metrics to Measure Utterance Classification Performance in Spoken Dialog Systems
- A Combination Approach to Cluster Validation Based on Statistical Quantiles Amparo Albalate
- ON AMBIGUITY DETECTION AND POSTPROCESSING SCHEMES USING CLUSTER ENSEMBLES
- TIME DOMAIN VOCAL TRACT LENGTH NORMALIZATION David Sundermann, Antonio Bonafonte
- Text-Independent Voice Conversion David Sundermann
- SYNTHER A NEW M-GRAM POS TAGGER David Sundermann and Hermann Ney
- Hard vs. Fuzzy Clustering for Speech Utterance Categorization
- A LANGUAGE RESOURCES GENERATION TOOLBOX FOR SPEECH SYNTHESIS David Sundermann
- RESIDUAL PREDICTION BASED ON UNIT SELECTION David Sundermann1,2
- Technology and Corpora for Speech to Speech Translation http://www.tc-star.org
- CALLER EXPERIENCE: A METHOD FOR EVALUATING DIALOG SYSTEMS AND ITS AUTOMATIC PREDICTION
- RESIDUAL PREDICTION David Sundermann1,2,3
- A First Step Towards Text-Independent Voice Conversion David Sundermann, Antonio Bonafonte
- OPTIMIZE THE OBVIOUS: AUTOMATIC CALL FLOW GENERATION D. Suendermann, J. Liscombe, R. Pieraccini
- Frequency Domain vs. Time Domain VTLN David Sundermann, Antonio Bonafonte
- Titel. Author(s) Copyright 2006 copyright holder, location
- "In a moment we will give you instructions on how to enable call blocking on your cell phone. We will also send these instructions by text message and to the email address on file. You can hang-up now, or hold for
- VTLN-BASED CROSS-LANGUAGE VOICE CONVERSION David Sundermann, Hermann Ney
- How to Drink from a Fire Hose: One Person Can Annoscribe 693 Thousand Utterances in One Month
- Lack of user expectations: Few people have used many multi-modal speech applications. Just as in the early days of speech-enabled IVRs, there is a general lack of expectation about how
- A NON-PARAMETERISED HIERARCHICAL POLE BASED CLUSTERING ALGORITHM (HPOBC)
- Are We There Yet? Research in Commercial Spoken Dialog Systems
- You Don't Have to Get Personal! IVR Customization via Situational Awareness
- Data Adaptive Dialog Systems David Attwater
- Call Classification with Hundreds of Classes and Hundred Thousands of Training Utterances ...
- The Speech Alignment Paradox David Sundermann1
- TOWARDS A MATHEMATICAL PROOF OF THE SPEECH ALIGNMENT PARADOX David Sundermann1,2
- TC-Star: Cross-Language Voice Conversion Revisited David Sundermann1,2
- TEXT-INDEPENDENT VOICE CONVERSION BASED ON UNIT SELECTION David Sundermann1,2,3
- A STUDY ON RESIDUAL PREDICTION TECHNIQUES FOR VOICE CONVERSION David Sundermann, Antonio Bonafonte
- TC-STAR: Evaluation Plan for Voice Conversion Technology David Sundermann1,2
- Voice Conversion: State-of-the-Art and Future Work David Sundermann
- Voice Conversion Using Exclusively Unaligned Training Data David Sundermann, Antonio Bonafonte
- VTLN-BASED VOICE CONVERSION David Sundermann and Hermann Ney
- VOICE CONVERSION MATLAB TOOLBOX David Sundermann
- DRESDEN UNIVERSITY of TECHNOLOGY DEPARTMENT of ELECTRICAL ENGINEERING and
- DRESDEN UNIVERSITY of TECHNOLOGY DEPARTMENT of ELECTRICAL ENGINEERING
- CALL CLASSIFICATION FOR AUTOMATED TROUBLESHOOTING ON LARGE CORPORA Keelan Evanini1,2
- DEPLOYING CONTENDER: EARLY LESSONS IN DATA, MEASUREMENT, AND TESTING OF MULTIPLE CALL FLOW DECISIONS
- Error Measures and Bayes Decision Rules Revisited with Applications to POS Tagging
- ELS TALPS TAMB PARLEN. Lnies de recerca en sntesi de la parla al centre TALP
- D. Suendermann, J. Liscombe, K. Evanini, K. Dayanidhi, R. Pieraccini SpeechCycle, Inc., New York City, USA
- SPEECH UTTERANCE CATEGORISATION GIVEN ONE TRAINING UTTERANCE PER CATEGORY
- General notes Conventions used throughout this exam
- Topic and Emotion Classification of Customer Surveys
- 1 Predicate logic (4 pts) Translate the following natural language sentences into formulas of predicate
- General notes Several tasks contain multiple choice or true/false questions. While it may be
- General notes When calculating results using Octave, please provide respective code snippets
