Determination of articulatory positions from speech acoustics by applying dynamic articulatory constraints

نویسندگان

  • Shin Suzuki
  • Takeshi Okadome
  • Masaaki Honda
چکیده

A method for determining articulatory parameters from speech acoustics is presented. The method is based on a search of an articulatory-acoustic codebook which is designed from simultaneous observation data of articulatory motions and speech acoustics. The codebook search employs dynamic constraints on acoustic behavior as well as articulatory behavior. There are two constrains. One of the constraints is use of spectral segments in the codebook search and the other is use of the smoothness of articulatory trajectories in the articulatory parameter path search. The articulatory parameters are determined by selecting the articulatory code vector in the codebook which minimizes the weighted distance measure of segmental spectral distance and squared distance between succeeding articulatory parameters. An experiment was conducted to evaluate the e ciency of both constraints in determining of articulatory parameters by comparing the estimated and the observed articulatory parameters. The results show that an rms error between the estimated and observed articulatory parameter was about 2.0 mm on average, and the articulatory features for vowels and consonants are recovered well.

برای دانلود 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

Speaker verification based on the fusion of speech acoustics and inverted articulatory signals

We propose a practical, feature-level and score-level fusion approach by combining acoustic and estimated articulatory information for both text independent and text dependent speaker verification. From a practical point of view, we study how to improve speaker verification performance by combining dynamic articulatory information with the conventional acoustic features. On text independent spe...

متن کامل

Articulatory analysis using a codebook for articulatory based low bit-rate speech coding

Fundamental to the success of the articulatory based speech coding is the mapping from acoustics to articulatory description. As the mapping is not unique and based on articulatory continuity criteria, the non-uniqueness of the articulatory trajectories is solved using a forward dynamic network. In this paper, we present new results on forward dynamic network used to estimate articulatory traje...

متن کامل

Estimation of Articulatory Parameters

This paper presents our research work of estimating articulatory states and model parameters from speech acoustics. This work represents a prerequisite for a speech recognition system based on articulatory dynamical models. The model parameter estimation was based on the vowels obtained from 590 sentences of 59 speakers from TIMIT speech database, whereas the state estimation experiments have b...

متن کامل

Automatic speech recognition using dynamic bayesian networks with both acoustic and articulatory variables

Current technology for automatic speech recognition (ASR) uses hidden Markov models (HMMs) that recognize spoken speech using the acoustic signal. However, no use is made of the causes of the acoustic signal: the articulators. We present here a dynamic Bayesian network (DBN) model that utilizes an additional variable for representing the state of the articulators. A particular strength of the s...

متن کامل

From Acoustics to Articulation

The focus of this thesis is the relationship between the articulation of speech and the acoustics of produced speech. There are several problems that are encountered in understanding this relationship, given the non-linearity, variance and non-uniqueness in the mapping, as well as the differences that exist in the size and shape of the articulators, and consequently the acoustics, for different...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1998