A neural network based nonlinear feature transformation for speech recognition
نویسندگان
چکیده
A neural network based feature dimensionality reduction for speech recognition is described for accurate phonetic speech recognition. In our previous work, a neural network based nonlinear principal component analysis (NLPCA) was proposed as a dimensionality reduction approach for speech features. It was shown that the reduced dimensionality features are very effective for representing data for vowel classification. In this paper, we extend this neural network based NLPCA approach for phonetic recognition using continuous speech. The reduced dimensionality features obtained with NLPCA are used as the features for HMM phone models. Experimental evaluation using the TIMIT database shows that recognition accuracies with NLPCA reduced dimensionality features are higher than recognition rates obtained with original features, especially when a small number of states and mixtures are used for HMM phonetic models.
منابع مشابه
Persian Phone Recognition Using Acoustic Landmarks and Neural Network-based variability compensation methods
Speech recognition is a subfield of artificial intelligence that develops technologies to convert speech utterance into transcription. So far, various methods such as hidden Markov models and artificial neural networks have been used to develop speech recognition systems. In most of these systems, the speech signal frames are processed uniformly, while the information is not evenly distributed ...
متن کاملبهبود عملکرد سیستم بازشناسی گفتار پیوسته بوسیله ویژگی‌های استخراج شده از مانیفولدهای گفتاری در فضای بازسازی شده فاز
The design for new feature extraction methods out of the speech signal and combination of their obtained information is one of the most effective approaches to improve the performance of automatic speech recognition (ASR) system. Recent researches have been shown that the speech signal contains nonlinear and chaotic properties, but the effects of these properties are not used in the continuous ...
متن کاملروشی جدید در بازشناسی مقاوم گفتار مبتنی بر دادگان مفقود با استفاده از شبکه عصبی دوسویه
Performance of speech recognition systems is greatly reduced when speech corrupted by noise. One common method for robust speech recognition systems is missing feature methods. In this way, the components in time - frequency representation of signal (Spectrogram) that present low signal to noise ratio (SNR), are tagged as missing and deleted then replaced by remained components and statistical ...
متن کاملPattern Recognition in Control Chart Using Neural Network based on a New Statistical Feature
Today for the expedition of the identification and timely correction of process deviations, it is necessary to use advanced techniques to minimize the costs of production of defective products. In this way control charts as one of the important tools for the statistical process control in combination with modern tools such as artificial neural networks have been used. The artificial neural netw...
متن کاملشبکه عصبی پیچشی با پنجره‌های قابل تطبیق برای بازشناسی گفتار
Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...
متن کاملImproving the performance of MFCC for Persian robust speech recognition
The Mel Frequency cepstral coefficients are the most widely used feature in speech recognition but they are very sensitive to noise. In this paper to achieve a satisfactorily performance in Automatic Speech Recognition (ASR) applications we introduce a noise robust new set of MFCC vector estimated through following steps. First, spectral mean normalization is a pre-processing which applies to t...
متن کامل