Soft margin estimation with various separation levels for LVCSR
نویسندگان
چکیده
We continue our previous work on soft margin estimation (SME) to large vocabulary continuous speech recognition (LVCSR) in two new aspects. The first is to formulate SME with different unit separation. SME methods focusing on string-, word-, and phonelevel separation are defined. The second is to compare SME with all the popular conventional discriminative training (DT) methods, including maximum mutual information estimation (MMIE), minimum classification error (MCE), and minimum word/phone error (MWE/MPE). Tested on the 5k-word Wall Street Journal task, all the SME methods achieves a relative word error rate (WER) reduction from 17% to 25% over our baseline. Among them, phone-level SME obtains the best performance. Its performance is slightly better than that of MPE, and much better than those of other conventional DT methods. With the comprehensive comparison with conventional DT methods, SME demonstrates its success on LVCSR tasks.
منابع مشابه
Soft margin estimation of hidden Markov model parameters
We propose a new discriminative learning framework, called soft margin estimation (SME), for estimating parameters of continuous density hidden Markov models. The proposed method makes direct usage of the successful ideas of soft margin in support vector machines to improve generalization capability, and of decision feedback learning in minimum classification error training to enhance model sep...
متن کاملHard or Soft Classification? Large-margin Unified Machines.
Margin-based classifiers have been popular in both machine learning and statistics for classification problems. Among numerous classifiers, some are hard classifiers while some are soft ones. Soft classifiers explicitly estimate the class conditional probabilities and then perform classification based on estimated probabilities. In contrast, hard classifiers directly target on the classificatio...
متن کاملApplication of Soft Computing Methods for the Estimation of Roadheader Performance from Schmidt Hammer Rebound Values
Estimation of roadheader performance is one of the main topics in determining the economics of underground excavation projects. The poor performance estimation of roadheader scan leads to costly contractual claims. In this paper, the application of soft computing methods for data analysis called adaptive neuro-fuzzy inference system- subtractive clustering method (ANFIS-SCM) and artificial neu...
متن کاملA study on soft margin estimation of linear regression parameters for speaker adaptation
We formulate a framework for soft margin estimation-based linear regression (SMELR) and apply it to supervised speaker adaptation. Enhanced separation capability and increased discriminative ability are two key properties in margin-based discriminative training. For the adaptation process to be able to flexibly utilize any amount of data, we also propose a novel interpolation scheme to linearly...
متن کاملDETERMINATION OF OPTIMAL DISTANCE BETWEEN TWO ADJACENT STEEL FRAMES CONSIDERING STRUCTURE-SOIL-STRUCTURE INTERACTION EFFECTS USING PSO
This paper aims to obtain the optimal distance between the adjacent structures using Particle Swarm Optimization (PSO) algorithm considering structure-soil-structure systems; The optimization algorithm has been prepared in MATLAB software and connected into OpenSees software (where the structure-soil-structure system has been analyzed by the direct approach). To this end, a series of adjacent s...
متن کامل