[Automatic Speech Recognition using HTK]

INATEL - Instituto Nacional de Telecomunicações

INATEL - Instituto Nacional de Telecomunicações - Mestrado em Telecomunicações - Aluno: Ramon Mayor Martins

[Meus passos na pesquisa do Mestrado para Reconhecimento Automatico de Voz]

quarta-feira, 5 de novembro de 2014

Estudo VTLN

Filter Bank Analysis
http://www.ee.columbia.edu/ln/rosa/doc/HTKBook21/node54.html

VTLN
http://www1.icsi.berkeley.edu/Speech/docs/HTKBook/node61_mn.html

Postado por Ramon Mayor Martins às 10:26

Enviar por e-mail Postar no blog!Compartilhar no Twitter Compartilhar no Facebook Compartilhar com o Pinterest

Nenhum comentário:

Postar um comentário

Postagem mais recente Postagem mais antiga Página inicial

Assinar: Postar comentários (Atom)

!!! [REPOSITORIO]

Google Code: htk-Inatel
Google Docs: Testes Realizados e Configurações
Google Docs: Mapa de Arquivos
Scripts Voxforge
Google Docs: Apresentação: Métodos Alternativos para estimação do Fator de distorção ótimo no VTLN

About me

Ramon Mayor Martins
Unknown

Links: HTK

HTK - Reconhecimento (Itália)
!!!! HTK HMM - Covariance
HTK Search Forum
HTK Resumo ferramentas
HTK HVite - Likelihood
HTK Resumo de um reconhecedor (Sheffield Univ)
HTK (Mono-Tri-Tied compared) Triphone clustering in Finnish continuous speech recognition - Ursin
HTK Speech Research
!!! HTK Presentation (Feature Extraction, Modeling, HMMs, bigram...) ISCAS 2012
!!! HTK HMM Training and Test IN FLOWCHART ! (SPL Taiwan) !!!
!!! HTK Features Speech Data (Esquema VTLN) !!!
HTK Tipo de Refinamento em Sistemas (Bill Barney - CLSP)
HTK Tutorial (explica mistura gaussiana) (Giampiero KTH, Suecia)
HTK Tutorial of Building an LVCSR System - Splitting Mixture Number (Hsiang Lin, Taiwan)
HTK Hcopy (compare com outros)
HTK HList -Hparm.c (onde se enquadra as Variaveis)
HTK script Bigram example (Jin Yoon)
HTK Construir Trifones e Tied State (Ahmet Ural)
HTK First Steps (Spirit.blau)
HTK Introduction (Ricardo Gutierrez - CSE Tamu Texas)
HTK Tutorial (Singapore)
HTK Tutorial (ISIP -Joseph Picone)
HTK Tutorial (psi based in htkbook)
HTK Tutorial (Schiel)
HTK Tutorial 2 (Voxforge)
HTK Tutorial (Voxforge)
HTK: UFPA - PEE-0521 Automatic speech recognition (Prof. Aldebaro)
HTK Variaveis usadas (Principal)
HTK Error Messages
HTK Book (site Berkeley.edu)
HTK Book
HTK Digit Recognition (Scripts da Universidade de Stanford))
HTK Speech Research (Principal)

HTK Documentos Internet

HTK Development of Acoustic Model for Croatian Language Using HTK (sobre word penalty e grammar scale factor)
HTK Large Vocabulary Speech Recognition System (sobre word penalty e grammar scale factor)
HTK Automatic Speech Recognition

aparência numerique

aparência numerique

Email Contact Form with Twitter, Facebook & Skypegreat free widgetsWidgetboxMore info

Links: Speech Signal Processing

Audio Signal Processing (Roger Jang's - TH University - Taiwan)
!!! Processamento de Fala (ISEL - Portugal)
!!! Speech Parametrization using Mel Scale (Bilkent University - Turkey)
Padrao ETSI 201 108 - Front-end feature extraction algorithm
Feature Extraction from Speech (SLS Alemanha)
Front-end feature extraction algorithm
Speech Signal Processing (Brno University of Technology - Czech Rep.)

Links: Speech Recognition

Speech Recognition Tools (ISLE - Illinois Speech and Language Engineering)
Speech Recognition and Synthesis (CS 224S - Stanford - Dan Jurafsky - Lec 8/9/10)
Speech Recognition based on HMM (Brno Cz)
Speech Recognition Course (NTNU Taiwan)
Fundamentals of Speech Recognition Course (California Sta Barbara - Rabiner)
Effect of parameter variation on WER Performance (Mississipi State University - Patil,Suh)

Links: HMM

HMM- PUCRS
HMM - Hidden Markov and Maximum Entropy Models (Bianca - UFF)
HMM appropriate values for Baselines (HTK and Sphinx)
Speech Recognition using HMM (tem extraction features)

GMM e HMM

GMM - Samy Bengio
!!!GTA UFRJ
Universidade de Coimbra

Links: VTLN

VTLN (Warp Factor - Matlab source code - Efficient Pitch-based Estimation of VTLN Warp Factors - Arlo Faria EUROSPEECH)
!!! VTLN Methods no HTK (Speech adaptation of special voice classes - Bjornar - Norway)
!!! Implementation of Vocal Tract Lenght Normalization - A Study of Methods (by Brian Widmer)
Signal modeling for robust speech recognition with frequency warping (Yoon Kim Thesis - Stanford)
Fundamentos do VTLN (Robust Speech Recognition: Analysis and Equalization of Lombard - Hynek Boril - Doc Tesis - Prague,Czech)
VTLN in HTK (Contents of Vocal Tract Length Normalisation - Sarah - KTH)
Implementation of Vocal Tract Length Normalization for Phoneme Recognition on TIMIT
!!! VTLN Methods no HTK (Speech adaptation of special voice classes - Bjornar - Norway)

Artigos comparacao resultados:

[HTK-TIDIGIT-VTLN] Dynamic Vocal Tract Length Normalization in Speech Recognition
[HTK-TIDIGIT-20Khz] Using Hidden Markov Models in segmentation of speaker-independent connected-digits corpus
[VTLN HTK TIDIGIT] Dynamic Vocal Tract Length Normalization in Speech Recognition (Mats Blomberg, KTH Stockolm)
[HTK-TIDIGIT-MONO/TRIFONE] Docteur de Télécom Bretagne (Amehraye)
[VTLI-HTK-TIDIGIT] VTLI for ASR (Signal Processing Group - Alemanha)

Arquivo do blog

▼ 2014 (22)
- ▼ novembro (22)

Tema Simples. Tecnologia do Blogger.

Ramon Mayor Martins

Lattes: http://lattes.cnpq.br/6289204315531991

http://www.odinasr.blogspot.com/