Speech recognition using an enhanced FVQ based on a codeword dependent distribution normalization and codeword weighting by fuzzy objective function
نویسندگان
چکیده
The paper presents a new variant of parameter estimation methods for discrete hidden Markov models(HMM) in speech recognition. This method makes use of a codeword dependent distribution normalization(CDDN) and a distance weighting by fuzzy contribution in dealing with the problems of robust state modeling in a FVQ based modeling. The proposed method is compared with the existing techniques using speaker-independent phonetically balanced isolated words recognition. The results have shown that the recognition rate of the proposed method is improved 4.5% over the conventional FVQ based method and the distance weighting to the smoothing of output probability is more efficient than the distance based codeword weighting.
منابع مشابه
Fuzzy Vector Quantization on the Modeling of Discrete Hidden Markov Model for Speech Recognition
This paper applies fuzzy vector quantization (FVQ) to the modeling of Discrete Hidden Markov Model (DHMM) and then to improve the speech recognition rate for the Mandarin speech. Vector quantization based on a codebook is a fundamental process to recognize the speech signal by DHMM. A codebook will be first trained by K-means algorithms using Mandarin training speech. Then, based on the trained...
متن کاملPredictive vector quantization using the M-algorithm for distributed speech recognition
In this paper we present a predictive vector quantizer for distributed speech recognition that makes use of a delayed decision coding scheme, performing the optimal codeword searching by means of the M-algorithm. In single-path predictive vector quantization coders, each frame is coded with the closest codeword to the prediction error. However, prediction errors and quantization errors of futur...
متن کاملVoice conversion using precise speech alignment based on spectral property and eigen-codeword distribution
While voice conversion methods have been popularly applied to convert the speech signals uttered by a source speaker to a target speaker, frame-based voice conversion generally suffers from incorrect alignment using only spectral distance and therefore generate improper conversion results. In a parallel phone sequence, the alignment using minimum spectral distance between frame-based feature ve...
متن کاملAn MCE based classification tree using hierarchical feature-weighting in speech recognition
In this paper a hierarchical classification framework using the feature-weighting tree for the objective of applying diverse weighting to acoustic features is proposed for speech recognition. The hierarchical feature-weighting tree with a flexible structure complexity can be constructed optimally with the optimal splitting for the recognition confusion graph. Based on the minimum classification...
متن کاملAutomatic Speaker Recognition Using Fuzzy Vector Quantization
Speaker recognition (SR) is a dynamic biometric task. SR is a multidisplinary problem that encompasses many aspects of human speech, including speech recognition, language recognition, and speech accents. This technique makes it possible to use the speaker’s voice to verify his/her identity and provide controlled access to services. The Mel-frequency extraction method is leading approach for sp...
متن کامل