Space Details:
Key
ITSP
Name
Introduction to Speech Processing
Description
Created by
backstt1@aalto.fi (Mar 14, 2019)
Available Pages:
Introduction to Speech Processing
Preface
Introduction
Speech production and acoustic properties
Why speech processing?
Applications and systems structures
Basic representations and models
Waveform
Windowing
Autocorrelation and autocovariance
Spectrogram and the STFT
Cepstrum and MFCC
Deltas and Delta-deltas
Fundamental frequency (F0)
Linear prediction
Zero-crossing rate
Pitch-Synchoronous Overlap-Add (PSOLA)
Pre-processing
Pre-emphasis
Modelling tools in speech processing
Gaussian mixture model (GMM)
Linear regression
Neural networks
Non-negative Matrix and Tensor Factorization
Sub-space models
Vector quantization (VQ)
Speech analysis
Fundamental frequency estimation
Inverse filtering for glottal activity estimation
Speech enhancement
Echo cancellation
Multi-channel speech enhancement and beamforming
Noise attenuation
Transmission, storage and telecommunication
Basic tools
Entropy coding
Modified discrete cosine transform (MDCT)
Perceptual modelling in speech and audio coding
Code-excited linear prediction (CELP)
Design goals
Frequency-domain coding
Recognition tasks in speech processing
Paralinguistic speech processing
Speaker Recognition and Verification
Voice activity detection (VAD)
Wake-word and keyword spotting
Speech analysis and imaging for medical applications
Glottal inverse filtering
References
Evaluation of speech processing methods
Analysis of evaluation results
Objective quality evaluation
Other performance measures
Subjective quality evaluation
Computational models of human language processing
Speech Recognition
Speaker Diarization
Security and privacy in speech technology
Speech Synthesis
Concatenative speech synthesis
Statistical parametric speech synthesis