Inhalt

•  
   Acknowledgments
•  
   Summary
•  
   Contents
•  
   Introduction
•  
   Outline
•  
  How language comes to children
•  
   Child directed speech
•  
   Word segmentation
•  
   Statistical Learning
•  
   Metric segmentation
•  
   The principle of subtraction
•  
   Allophonic and articulatory cues
•  
   Syllable segmentation
•  
   Sonority sequencing principle
•  
   Maximum onset principle
•  
   Phonotactic learning
•  
   Phone segmentation
•  
   Vocabulary acquisition
•  
  Pattern recognition background
•  
   Clustering
•  
   Incremental clustering
•  
   Self-organizing neural nets
•  
  Probability density estimation
•  
   Parametric approaches
•  
   MAP
•  
   Non-parametric approaches
•  
   Information theory basics
•  
   HMMs
•  
   Parameter estimation
•  
   Model adaption
•  
   Statistical language modeling
•  
   Automatic speech recognition
•  
   Feature extraction
•  
   Acoustic modeling
•  
   Keyword Spotting
•  
   Confidence Measures
•  
   Neural networks for speech recognition
•  
  Symbolic models for speech acquisition
•  
   Symbolic sub-syllable learning of speech structure
•  
   Symbolic syllable structure learning
•  
   Symbolic word structure learning
•  
   Acoustic speech modeling
•  
   Implicit model-based speech clustering
•  
   Direct methods for speech segmentation
•  
   Model-based changed point detection
•  
   Syllable segmentation
•  
   Word acquisition
•  
   Acoustic model bootstrapping
•  
   Model
•  
  Computational requirements and constraints
•  
   Type of input speech
•  
   Speech representation
•  
   Order of bootstrapping
•  
   Processing principles
•  
   Coupling of speech unit representations
•  
   System overview
•  
  Phones
•  
   Unsupervised phone cluster learning
•  
   Phonotactic Learning
•  
  Syllables
•  
   Syllable spotting
•  
   Training segment generation
•  
   Incremental clustering of syllable segments
•  
   Regulation
•  
   Syllable transition modeling
•  
   Words
•  
   Top-down error correction
•  
   Basic syntax learning
•  
   Scientific contribution
•  
   What this model is not
•  
  Evaluation
•  
   Performance Metrics
•  
   Model Labeling
•  
   Segmentation quality
•  
   Kappa
•  
   Segmentation vs. clustering
•  
   Statistical learning quality
•  
   Corpora
•  
   Phones
•  
   Monosyllabic words
•  
   Semi-synthetic speech
•  
   Discrete speech
•  
   Child-directed read speech
•  
   Phones
•  
   Classification
•  
   Clustering
•  
   Phone-distributed word models
•  
   Phone language model
•  
   Phonotactic model
•  
   Syllabic parsing
•  
  Syllables
•  
   Model initialization
•  
   Clustering process properties
•  
   Spotting performance
•  
   Subtraction learning
•  
   Syllable Grammar learning
•  
  Words
•  
   Lexical Learning
•  
  Embodied speech acquisition
•  
   Grounded word acquisition
•  
   Linking speech perception and production
•  
   Speech production architecture
•  
   Interaction
•  
   Experimental results
•  
   Summary and discussion
•  
   Discussion and outlook
•  
   Bibliography