Investigating Feature Spaces for Isolated Word Recognition

Grazina Korvel; Gintautas Tamulevicus; Povilas Treigys; Jolita Bernataviciene; Bożena Kostek

doi:10.15388/damss.2018.1

Investigating Feature Spaces for Isolated Word Recognition

Abstrakt

Much attention is given by researchers to the speech processing task in automatic speech recognition (ASR) over the past decades. The study addresses the issue related to the investigation of the appropriateness of a two-dimensional representation of speech feature spaces for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and timefrequency signal representation converted to the investigative feature spaces. In particular, fractal dimension features of the signal were chosen for the time domain, and two feature spaces were investigated for the frequency domain, namely: frequency tracks obtained from the frequencies and amplitudes of the detected spectral peaks and the modified chromagrams. Both are constructed from a series of short-time Fourier transforms, which were computed along the window speech signal in the time domain. Due to the fact that deep learning requires a sufficiently large training set as the size of the corpus may significantly influence the outcome, thus for the data augmentation purpose, the created dataset was extended by adding various noise levels and mixed with the speech signal. In order to evaluate the applicability of implemented feature spaces for isolated word recognition task, three experiments were conducted: a 10-word, a 70-word, and a 111-word cases were analyzed.

Cytowania

0

CrossRef
0

Web of Science
0

Scopus

Autorzy (5)

Grazina Korvel dr
Gintautas Tamulevicus
Povilas Treigys
Jolita Bernataviciene
Bożena Kostek prof. dr hab. inż.

Cytuj jako

Pełna treść

pełna treść publikacji nie jest dostępna w portalu

Słowa kluczowe

AUTOMATYCZNE ROZPOZNAWANIE MOWY, SPLOTOWE SIECI, GŁĘBOKIE UCZENIE, CHROMAGRAMY, WYMIAR FRAKTALNY

Informacje szczegółowe

Kategoria:

Aktywność konferencyjna

Typ:

publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)

Tytuł wydania:

DATA ANALYSIS METHODS FOR SOFTWARE SYSTEMS strony 47 - 47

Język:

angielski

Rok wydania:

2018

Opis bibliograficzny:

Korvel G., Tamulevicus G., Treigys P., Bernataviciene J., Kostek B.: Investigating Feature Spaces for Isolated Word Recognition// DATA ANALYSIS METHODS FOR SOFTWARE SYSTEMS/ Druskieniki: , 2018, s.47-47

DOI: