Trajectory Clustering for Solving the Trajectory Folding Problem in Automatic Speech Recognition
نویسندگان
چکیده
منابع مشابه
Speech trajectory clustering for improved speech recognition
Context dependent modelling is known to improve recognition performance for automatic speech recognition. One of the major limitations, especially of approaches based on Decision Trees, is that the questions that guide the search for effective contexts must be known in advance. However, the variation in the speech signals is caused by multiple factors, not all of which may be known during the t...
متن کاملTrajectory Clustering Using Longer Length Units for Automatic Speech Recognition
One of the major deficiencies of conventional hidden Markov modelling (HMM) is known as the trajectory folding phenomenon. Multipath Models can solve the trajectory folding problem by assuming that a large part of the variation in acoustic data can be attributed to different observation classes and which can then be modelled separately. In this paper, we present an approach to automatically clu...
متن کاملthe algorithm for solving the inverse numerical range problem
برد عددی ماتریس مربعی a را با w(a) نشان داده و به این صورت تعریف می کنیم w(a)={x8ax:x ?s1} ، که در آن s1 گوی واحد است. در سال 2009، راسل کاردن مساله برد عددی معکوس را به این صورت مطرح کرده است : برای نقطه z?w(a)، بردار x?s1 را به گونه ای می یابیم که z=x*ax، در این پایان نامه ، الگوریتمی برای حل مساله برد عددی معکوس ارانه می دهیم.
15 صفحه اولEM Algorithm with Split and Merge in Trajectory Clustering for Automatic Speech Recognition
In this paper, we introduce two reformulated versions of the standard EM algorithm, namely Successive Split EM and Split and Merge EM, to relax the problem of initialization dependence in datadriven Speech Trajectory Clustering. These two algorithms allow us to prevent the EM procedure in Trajectory Clustering from ending in a local maximum of the likelihood surface. Thus, the new methods will ...
متن کاملParametric trajectory models for speech recognition
The basic motivation for employing trajectory models for speech recognition is that sequences of speech features are statistically dependent and that the e ective and e cient modeling of the speech process will incorporate this dependency. In our previous work [1] we presented an approach to modeling the speech process with trajectories. In this paper we continue our development of parametric t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Audio, Speech and Language Processing
سال: 2007
ISSN: 1558-7916
DOI: 10.1109/tasl.2007.894529