Towards unsupervised training of the classifier-based speech translator
نویسندگان
چکیده
Concept classification has been proven to be a useful translation method for speech-to-speech translation applications. However, preparing training data for classifier is a cumbersome task for human annotators. An unsupervised training method is introduced here that is based on utterance clustering. A technique to measure the distance between two utterances, based on the concepts they express, along with an appropriate clustering method has been adapted.
منابع مشابه
Unsupervised data processing for classifier-based speech translator
Concept classification has been used as a translation method and has shown notable benefits within the suite of speech-tospeech translation applications. However, the main bottleneck in achieving an acceptable performance with such classifiers is the cumbersome task of annotating large amounts of training data. Any attempt to develop a method to assist in, or to completely automate, data annota...
متن کاملUnsupervised Acoustic Model Training for Simultaneous Lecture Translation in Incremental and Batch Mode
In this work the theoretical concepts of unsupervised acoustic model training and the application and evaluation of unsupervised training schemes are described. Experiments aiming at speaker adaptation via unsupervised training are conducted on the KIT lecture translator system. Evaluation takes place with respect to training e ciency and overall system performance in dependency of the availabl...
متن کاملبهبود بازشناسی چهره با یک تصویر از هر فرد به روش تولید تصاویر مجازی توسط شبکههای عصبی
This paper deals with the problem of face recognition from a single image per person by producing virtual images using neural networks. To this aim, the person and variation information are separated and the associated manifolds are estimated using a nonlinear neural information processing model. For increasing the number of training samples in neural classifier, virtual images are produced for...
متن کاملCombining Classifier Guided by Semi-Supervision
The article suggests an algorithm for regular classifier ensemble methodology. The proposed methodology is based on possibilistic aggregation to classify samples. The argued method optimizes an objective function that combines environment recognition, multi-criteria aggregation term and a learning term. The optimization aims at learning backgrounds as solid clusters in subspaces of the high...
متن کاملCombining Classifier Guided by Semi-Supervision
The article suggests an algorithm for regular classifier ensemble methodology. The proposed methodology is based on possibilistic aggregation to classify samples. The argued method optimizes an objective function that combines environment recognition, multi-criteria aggregation term and a learning term. The optimization aims at learning backgrounds as solid clusters in subspaces of the high...
متن کامل