Hidden Markov Model-based approach for nasalized vowels recognition in spontaneous speech

نویسندگان

  • András Beke
  • Viktória Horváth
چکیده

In this study, oral and nasalized vowels were analysed based on Hungarian spontaneous speech corpus. Although such results are generally based on analyses of isolated, read-aloud sentences, the authors suggested it is questionable that they are also true of spontaneous types of speech. There is a lack of agreement in the literature as to which measurable acoustic parameters correlate of nasality. MFCC as robust feature was presented earlier for nasalized vowel detection combined with SVM classifier. In this research, we investigated the use MFCC and HMM for automatic nasalized vowel recognition. Results support the view i) regressive nasalization could be classified with better accuracy than progressive nasalization, ii) the degree of nasalization strongly depends on the vowel quality, iii) low vowels show a large degree of articulatory nasalization, however, the acoustic consequences are smaller, therefore the perceived degree of nasalization is either similar or lesser than for higher vowels.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Improving Phoneme Sequence Recognition using Phoneme Duration Information in DNN-HSMM

Improving phoneme recognition has attracted the attention of many researchers due to its applications in various fields of speech processing. Recent research achievements show that using deep neural network (DNN) in speech recognition systems significantly improves the performance of these systems. There are two phases in DNN-based phoneme recognition systems including training and testing. Mos...

متن کامل

Comparative Analysis of Arabic Vowels using Formants and an Automatic Speech Recognition System

Arabic, the world’s second most spoken language in terms of number of speakers, has not received much attention from the traditional speech processing research community. This study is specifically concerned with the analysis of vowels in modern standard Arabic dialect. The first and second formant values in these vowels are investigated and the differences and similarities between the vowels e...

متن کامل

A HMM-based recognition system for perceptive relevant pitch movements of spontaneous German speech

This paper presents an HMM-based recognition system for perceptive relevant pitch movements of spontaneous German speech. The pitch movements are de ned according to the perceptively and phonetically motivated IPO-approach to intonation. For recognition we use a hybrid approach combining polynomial classi cation with Hidden Markov Modelling. The recognition is based only on the speech signal, i...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015