Learn More
In this paper, we propose a speech recognition engine using hybrid model of Hidden Markov Model (HMM) and Gaussian Mixture Model (GMM). Both the models have been trained independently and the respective likelihood values have been considered jointly and input to a decision logic which provides net likelihood as the output. This hybrid model has been(More)
Noise robustness is one of the most challenging problem in automatic speech recognition. The goal of robust feature extraction is to improve the performance of speech recognition in adverse conditions. The mel-scaled frequency cepstral coefficients (MFCCs) derived from Fourier transform and filter bank analysis are perhaps the most widely used front-ends in(More)
In this paper, a feature extraction method that is robust to additive background noise is proposed for automatic speech recognition. Since the background noise corrupts the autocorrelation coefficients of the speech signal mostly at the lower orders, while the higher-order autocorrelation coefficients are least affected, this method discards the lower order(More)
This paper presents a new front-end for robust speech recognition. This new front-end scenario focuses on the spectral features of the filtered speech signals in the autocorrelation domain. The autocorrelation domain is well known for its pole preserving and noise separation properties. In this paper, a novel method for robust speech extraction is proposed(More)
This paper presents the implementation of adaptive algorithms like Least Mean Square (LMS) and Normalized Least Mean Square (NLMS) in the frequency domain and their comparison to that implemented in the time domain. Adaptive filtering using adaptive algorithm in frequency domain can be done by taking Fourier Transform of input signal and independent weigh(More)
With the rapid growth in digital content and user's needs, the complexity of ranking mechanism utilized in digital libraries is increasing. Ranking plays a vital role in digital libraries to rank publications or scientific literature so that researchers can easily explore the search results list and find the desired content against the query. In this paper,(More)
This paper presents a new feature vector set for noisy speech recognition in autocorrelation domain. The autocorrelation domain is well known for its pole preserving and noise separation properties. In this paper we will use the autocorrelation domain as an appropriate candidate for robust feature extraction. In our approach, extraction of mel frequency(More)
This paper proposes profiling and optimization of Variable Step Size (VSS) algorithm for adaptive noise cancellation by implementing the algorithm in DSP Processor TMS320C6713. The implementation of VSS algorithm in DSK (DSP Starter Kit) includes optimization of algorithms using various optimization techniques via profiling. Code Compose Studio (CCS an(More)
Text to speech synthesis means conversion of written text into spoken words. In order to make speech more natural and intelligible one way is to concatenate the prerecorded units of speech using unit selection algorithm. These units are stored in one place from where they are played back, called speech corpus. There are various standard corpuses available(More)