The Vocal Joystick Vowel Corpus, by Washington University, was used to study monophthongs pronounced by native English speakers. The objective of this study was to quantitatively measure the extent at which speech recognition methods can distinguish between similar sounding vowels. In particular, the phonemes /@/, /æ/, /A:/ and /2/ were analysed. 748 sound files from the corpus were used and su...

A novel tone quality improvement method for a bone conduction voice is presented. In the present method, the tone quality of the bone conduction voice is converted to the similar quality of the air conduction voice. For the voice conversion, the present method uses a codebook, which consists of various paired code vectors of the bone and air conduction voices. The deltaand mel-cepstral coeffici...

Speech recognition is an important field of digital signal processing. Automatic Speaker Recognition (ASR) objective is to extract features, characterize and recognize speaker. Mel Frequency Cepstral Coefficients (MFCC) is most widely used feature vector for ASR. MFCC is used for designing a text dependent speaker identification system. In this paper the DSP processor TMS320C6713 with Code Comp...

Speaker verification techniques neglect the short-time variation in the feature space even though it contains speaker related attributes. We propose a simple method to capture and characterize this spectral variations through the eigenstructure of the sample covariance matrix. This covariance is computed using sliding window over spectral features. The newly formulated feature vectors represent...

This paper presents new Speaker Identification and Speaker Verification systems based on the use of new feature vectors extracted from the speech signal. The proposed structure combine between the most successful Mel Frequency Cepstral Coefficients and new features which are the Short Time Zero Crossing Rate of the signal. A comparison between speaker recognition systems based on Gaussian mixtu...

Recent work demonstrates impressive success of the bottleneck (BN) feature in speech recognition, particularly with deep networks plus appropriate pre-training. A widely admitted advantage associated with the BN feature is that the network structure can learn multiple environmental conditions with abundant training data. For tasks with limited training data, however, this multi-condition traini...

This paper presents a new signal-processing technique motivated by the physiology of human auditory system. In this approach, auditory hair cells are modeled as damped oscillators that are stimulated by bandlimited time domain speech signals acting as forcing functions. Oscillation synchrony is induced by time aligning and three-way coupling of the forcing functions across the individual bands ...

Perceptual harmonic cepstral coefficients (PHCC) are proposed as features to extract from speech for recognition in noisy environments. A weighting function, which depends on the prominence of the harmonic structure, is applied to the power spectrum to ensure accurate representation of the voiced speech spectral envelope. The harmonics weighted power spectrum undergoes mel-scaled band-pass filt...