Improvements to fMPE for discriminative training of features
نویسنده
چکیده
fMPE is a previously introduced form of discriminative training, in which offsets to the features are obtained by training a projection from a high-dimensional feature space based on posteriors of Gaussians. This paper presents recent improvements to fMPE, including improved high-dimensional features which are easier to compute, and improvements to the training procedure. Other issues investigated include cross-testing of fMPE transforms (i.e. using acoustic models other than those with which the fMPE was trained) and the best way to train the Gaussians used to obtain the vector of posteriors.
منابع مشابه
Improvements to fMPE for discrimin
fMPE is a previously introduced form of discriminative training, in which offsets to the features are obtained by training a projection from a high-dimensional feature space based on posteriors of Gaussians. This paper presents recent improvements to fMPE, including improved high-dimensional features which are easier to compute, and improvements to the training procedure. Other issues investiga...
متن کاملDiscriminatively trained features using fMPE for multi-stream audio-visual speech recognition
fMPE is a recently introduced discriminative training technique that uses the Minimum Phone Error (MPE) discriminative criterion to train a feature-level transformation. In this paper we investigate fMPE trained audio/visual features for multistream HMM-based audio-visual speech recognition. A flexible, layer-based implementation of fMPE allows us to combine the the visual information with the ...
متن کاملMinimum Phone Error (MPE) Model and Feature Training on Mandarin Broadcast News Task
The Minimum Phone Error (MPE) criterion for discriminative training was shown to be able to offer acoustic models with significantly improved performance. This concept was then further extended to Featurespace Minimum Phone Error (fMPE) and offset fMPE for training feature parameters as well. This paper reviews the concept of MPE and reports the experiments and results in performing MPE, fMPE a...
متن کاملCompacting discriminative feature space transforms for embedded devices
Discriminative training of the feature space using the minimum phone error objective function has been shown to yield remarkable accuracy improvements. These gains, however, come at a high cost of memory. In this paper we present techniques that maintain fMPE performance while reducing the required memory by approximately 94%. This is achieved by designing a quantization methodology which minim...
متن کاملRegularized feature-space discriminative adaptation for robust ASR
Model-space adaptation techniques such as MLLR and MAP are often used for porting old acoustic models into new domains. Discriminative schemes for model adaptation based on MMI and MPE objective functions are also utilized. For feature-space adaptations, one extension to the wellknown feature-space discriminative training (fMPE) algorithm, feature-space discriminative adaptation, was recently p...
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 2005