A study of line spectrum pair frequencies for vowel recognition

نویسنده

  • Kuldip K. Paliwal
چکیده

The line spectrum pair (LSP) frequency represer.iation has recent:y been proposed as an alternative linear prediction (LP) parametric representation. In the context of speech coding, this representation shows better quantization properties than the other LP parametric representations. In the present paper, the LSP representation is studied for speech recognition. Several distance measures based on this representation are investigated on a steady-state vowel recognition task. The weighted LSP distance measure is found to result in the best performance. The performance of the weighted LSP distance measure is compared with that of the other popular LP distance measures (such as the Itakura. cepstral, weighted cepstral, root-power-sum, log 'area ratio and reflection coefficient distance measures). The weighted LSP distance measure is found to perform significantly better than these popular LP distance measures. Rdsum6. La repr~septation en frdquence sur base d'un "'line spectrum pair" a 6t6 proposde en tant que variante de la repr6sentation paramdtrique par prddiction lindaire. Darts le contexte du codage du signal de parole, la structure LSP poss~de de meilleures propridtC, de quantification que les reprdsentations LPC plus classiques. Dans cet article, la prdsen-tation LSP est 6tudide dans le contexte de la reconnaissance automatique de la parole. Plusieurs mesures de distance sur base d'un moddle LSP sont 6tudides dans le cadre d'une t~che de reconnaissance de voyelles soutenues. La mesure LSP ponddrde s'avdre 6tre la meilleure. Elle a 6t6 comparde /l d'autres mesures de distances mieux connues (c'est-:a-dire tes distances d'Itakura, cepstrale, cepstrale ponddrde, de racine-puissance-somme, du rapport Iogarithmique d'aires et des coefficients de rdflexion). La distance LSP ponddrdc permet un meilleur taux de reconnaissance que les autres mesures indiqudes.

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

The Effect of English Vowel-Recognition Training on Beginner and Advanced Iranian ESL Learners

This study was an attempt to investigate the effect of vowel-recognition training on beginner and advanced Iranian ESL learners. A total of 36 adult Iranian ESL learners (18 advanced and 18 beginners) who were students of various majors at Memorial University (MUN) were recruited for the study. Advanced participants had the experience of living in Canada for at least three years while beginners...

متن کامل

Acoustic Analysis of Persian EFL Learners' Pronunciation of English Vowels

This paper reports the results of an experimental study on non-native production of English vowels. Two groups of Persian EFL learners varying in language proficiency were tested on their ability to produce the nine plain vowels of American English. Vowel production accuracy was assessed by means of acoustic measurements. Ladefoged and Maddison’s (1996) F1 F2 measurements for American English v...

متن کامل

پیش‌بینی قابلیت فهم همخوان‌ها در افراد دارای شنوایی عادی با استفاده از مدل‌های میکروسکوپی دارای معیار فاصله‌ مختلف در بازشناساگر خودکار گفتار

In this study, recognition rates of consonants available in vowel-consonant-vowel structure in hearing tests and two microscopic models will be investigated. Such a syllable structure doesn’t exist in Farsi and Azerbaijani languages, but since the goal is only recognition of middle phoneme, according to hearing tests, listeners are able to properly recognize phonemes in clean speech conditions....

متن کامل

Spectral normalization employing hidden Markov modeling of line spectrum pair frequencies

This paper proposes a spectral normalization approach in which the acoustical qualities of an input speech waveform are mapped onto that of a desired neutral voice. Such a method can be e ective in reducing the impact of speaker variability such as accent, stress, and emotion for speech recognition. In the proposed method, the transformation is performed by modeling the temporal characteristics...

متن کامل

A study of two-formant models for vowel identification

An experiment has been performed where various two-formant models reported in the literature were assessed as to their ability to predict the formant frequencies obtained in a vowel identification task. An alternative model is proposed in which the auditory processing of vowel sounds is assumed to take place in two stages: a peripheral processing stage and a central processing stage. In the per...

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:
  • Speech Communication

دوره 8  شماره 

صفحات  -

تاریخ انتشار 1989