Beruflich Dokumente
Kultur Dokumente
Grading Criteria
Major Topics
Modeling
Acoustic Theory of Speech Production and Perception
Acoustic-Phonetics
Time-Frequency Analysis
Speech pre-processing
Supervised Learning
Unsupervised Learning
Speech Structure
Rule-based Grammar
Statistical Grammar
Syllabus
(Weeks 1-8)
Week
Subject
Course Introduction
2-3
4-6
Machine Learning
Supervised Learning
Unsupervised Learning
Syllabus
(Weeks 9-16)
Week
Subject
8-10
11-14
Speech pre-processing
The Fourier Transform (FT) and the Fast Fourier Transform (FFT)
The Wavelet transform (WT) and the Wavelet Packet Transform (WPT)
14-15
Language Modeling
Semantics
16
Finals Week
Take-home final
Speech synthesis
CSRLU Toolkit
AT&T Natural Voices
Speech effects
pitch bending
Chorus effects
Grammar modeling
Dragon Dictate
SAPI (Microsofts Speech API)
CSRLU Toolkit
Synthetic Shakespeare
Speaker recognition
Acoustic Biometrics
Accent recognition
Language training
Resources
(Things you will need)
Textbook:
Speech And Language Processing, 2nd Edition,
Jurafsky & Martin Prentice Hall, 2009
Matlab/Octave, Audacity, Java, C++, etc.
Various papers to be announced
The goal of the Semester Project is to apply and generalize the presented concepts by developing a
Big Idea in a team setting.
Synthetic Shakespeare
The Cocktail Party Effect
Concatenative Speech Synthesis
Prosody Detection & Synthesis
Accent Recognition
Harmony Generation
Emotion Recognition
Synthetic Beatles, Beethoven, etc.
Synthetic Shakespeare
The Cocktail Party Effect
Concatenative Speech Synthesis
Prosody Detection & Synthesis
Accent Recognition
Harmony Generation
Emotion Recognition
Synthetic Beatles, Beethoven, etc.
In Brief
A Quick Overview
Natures Model: