Improving the Sampling of the Null Space of the Acoustic-to-Articulatory Mapping
نویسندگان
چکیده
This paper presents a new method for sampling the null space of the acoustic-to-articulatory mapping, which is considerably faster and more accurate than the previous method presented by Ouni and Laprie [4]. This is achieved by using a simple stochastic exploration of the articulatory space instead of complex linear programming techniques. This new method allows for a much faster and more accurate inversion process.
منابع مشابه
Exploring the null space of the acoustic-to- articulatory inversion using a hypercube codebook
Our acoustic to articulatory inversion method exploits an original codebook representing the articulatory space by hypercubes. The articulatory space is decomposed into regions where the articulatory-to-acoustic mapping is linear. Each region is represented by a hypercube. The inversion procedure retrieves articulatory vectors corresponding to an acoustic entry from the hypercube codebook. The ...
متن کاملImproving acoustic-to-articulatory inversion by using hypercube codebooks
This paper presents an articulatory codebook construction method which gives a good space coverage with a limited number of points. We represent the articulatory space by hypercubes. Therefore the articulatory space is decomposed into regions represented by few number of points. We describe our interpolation method to retrieve points from the hypercube and the inversion method based on the same...
متن کاملA study of the French vowels through vocal tract using an acoustic-to-artic
This paper presents a study of the articulatory properties of French vowels using an acoustic-to-articulatory inversion method. The advantage of such an approach is that all the possible articulatory configurations can be studied independently of any articulatory preferences linked with a given speaker. Furthermore, it bypasses the issue of acquiring a vast amount of articulatory data by medica...
متن کاملA variational approach for estimating vocal tract shapes from the speech signal
This paper presents a novel approach to recovering articulatory trajectories from the speech signal using a variational calculus method and Maeda’s articulatory model. The acoustic-toarticulatory mapping is generally assessed by a double criterion: the acoustic proximity of results to acoustic data and the smoothness of articulatory trajectories. Most of the existing methods are unable to explo...
متن کاملHierarchical partition of the articulatory state space for overlapping-feature based speech recognition
We describe our recent work on improving an overlapping articulatory feature (sub-phonemic) based speech recognizer with robustness to the requirement of training data. A new decision-tree algorithm is developed and applied to the recognizer design which results in hierarchical partitioning of the articulatory state space. The articulatory states associated with common acoustic correlates, a ph...
متن کاملذخیره 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 2008