Fundamentals of Speech Recognition and Generation - NPFX038
Title: Základy rozpoznávání a generování mluvené řeči
Guaranteed by: Student Affairs Department (32-STUD)
Faculty: Faculty of Mathematics and Physics
Actual: from 2022
Semester: winter
E-Credits: 6
Hours per week, examination: winter s.:2/2, C+Ex [HT]
Capacity: unlimited
Min. number of students: unlimited
4EU+: no
Virtual mobility / capacity: no
State of the course: taught
Language: Czech
Teaching methods: full-time
Is provided by: NPFL038
Guarantor: Mgr. Nino Peterek, Ph.D.
Class: DS, matematická lingvistika
Informatika Mgr. - Matematická lingvistika
Classification: Informatics > Computer and Formal Linguistics
Pre-requisite : {NXXX011, NXXX012, NXXX013, NXXX070, NXXX071}
Incompatibility : NPFL038
Interchangeability : NPFL038
Opinion survey results   Examination dates   WS schedule   Noticeboard   
Annotation -
This course deals with speech recognition and generation tasks and feature extraction of voice and utterance characteristics. Of particular interest will be topics related to Hidden Markov Models as applied to speech (FFT, n- dimensional clustering, Gaussian mixtures, parameter value extraction from data, phonetic representation, prosodic analysis etc.) and to their DNN-HMM hybrid models. Preparation and training of own speech recognition and generation models.
Last update: Mírovský Jiří, RNDr., Ph.D. (11.05.2022)
Course completion requirements -

Oral examination and project presentation.

The practical part is controlled through the preparation and presentation of own models for speech recognition and generation.

The presentation is repeatable.

Last update: Peterek Nino, Mgr., Ph.D. (10.06.2019)
Literature -
Gernot A. Fink, Markov Models for Pattern Recognition, Springer, 2014

Steve Young, Dan Kershaw, Julian Odell, Dave Ollason, Valtcho Valtchev, Phil Woodland, The HTK Book, Cambridge, Entropic Ltd. http://htk.eng.cam.ac.uk, 1995-2007

Zdena Palková, Fonetika a fonologie češtiny, Karolinum, Praha, 1997

Dong Yu,Li Deng, Automatic Speech Recognition A Deep Learning Approach, 2015

NPFL038 Details and News

Last update: Peterek Nino, Mgr., Ph.D. (11.05.2022)
Requirements to the exam -

Exam covers theoretical part of the course (syllabus), there is only oral exam.

Finalisation of practical part is not necessary before the exam.

Last update: Peterek Nino, Mgr., Ph.D. (13.10.2017)
Syllabus -

Introduction to Speech Production and Perception.

General Principles of Automatic Speech Recognition (HMM)

  • Isolated Word Recognition,
  • Output Probability Specification,
  • Baum-Welch Re-Estimation,
  • Recognition and Viterbi Decoding,
  • Continuous Speech Recognition,
  • Speaker Adaptation.

HTK Tools description

  • Data Preparation Tools,
  • Training Tools,
  • Recognition Tools,
  • Analysis Tool.

Data Preparation

  • the Task Grammar,
  • the Language Model,
  • the Dictionary,
  • Recording the Data, Creating the Transcription Files, Coding the Data.

Creating Monophone HMMs

  • Creating Flat Start Monophones,
  • Fixing the Silence Models,
  • Realigning the Training Data.

Creating Triphones HMMs

  • Making Triphones from Monophones,
  • Making Tied-State Triphones,
  • Splitting States.

Recogniser Evaluation.

General Principles of Automatic Speech Generation.

Speech Prosody Analysis.

Last update: Peterek Nino, Mgr., Ph.D. (13.10.2017)