In this study, we propose a speaker-dependent WaveNet vocoder, a method of synthesizing speech waveforms with WaveNet, by utilizing acoustic features from existing vocoder as auxiliary features of WaveNet. It is expected that WaveNet can learn a sample-by-sample correspondence between speech waveform and acoustic features. The advantage of the proposed method is that it does not require (1) exp...

This paper presents a feature parameter transformation method using ICA (independent component analysis) for text independent speaker identification of telephone speech. ICA is a signal processing technique which can separate linearly mixed signals into statistically independent signals. The proposed method transforms them into new vectors using ICA assuming that the cepstrum vectors of the tel...

This paper deals with LP based Mel-Generalized cepstrum which has been used as front-end for Hidden Markov Model (HMM) based speech recognition and it incorporates equal-loudness power law as well as auditory-like frequency resolution. To utilize the generalized cepstral representation, the model spectrum can be varied continuously from the all-pole spectrum to that represented by the cepstrum ...

Speaker independent discrimination of four confusable consonants in the strictly fixed context of six vowels is considered. The consonants are depicted by features of consonant’s stationary part and changing rate of features (delta features) in transition from consonant to the following vowel. The mel frequency cepstrum (MFCC), linear prediction cepstrum (LPCC), recursive filter (F12) features ...

In this work, linear and nonlinear feature transformations have been experimented in ASR front end. Unsupervised transformations were based on principal component analysis and independent component analysis. Discriminative transformations were based on linear discriminant analysis and multilayer perceptron networks. The acoustic models were trained using a subset of HUB5 training data and they ...

It is well-known that HMMs only of the basic structure cannot capture the correlations among successive frames adequately. In our previous work, to solve this problem, segmental unit HMMs were introduced and their e ectiveness was shown. And the integration of cepstrum and cepstrum into the segmental unit HMMs was also found to improve the recognition performance in the work. In this paper, we ...

We compared three different channel normalisation (CN) methods in the context of a connected digit recognition task over the phone: ceptrum mean substraction (CMS), RASTA filtering and the Gaussian dynamic cepstrum reprsentation (GDCR). Using a small set of context-independent (CI) continuous Gaussian mixture hidden Markov models (HMMs) we found that CMS and RASTA outperformed the GDCR techniqu...

It has been shown that detailed information from non-stationary signals such as speech are better represented by an acoustic image, a two dimensional feature representation [10]. Several time frequency representations such as the spectrogram, Wigner-ville and choi-williams distribution have been proposed [6] while the acoustic images based on the two dimensional root cepstrum analysis (TDRC) is...

The following article presents a new real time implementation of an iterative cepstrum based spectral envelope estimation technique that was originally published under the name true envelope. Because the original algorithm is hardly known outside Japan we will first describe the algorithm and compare it to the standard techniques, i.e. LPC and discrete cepstrum. The estimation properties are co...

Speech corpus is one of the major components in a Speech Processing System where one of the primary requirements is to recognize an input sample. The quality and details captured in speech corpus directly affects the precision of recognition. The current work proposes a platform for speech corpus generation using an adaptive LMS filter and LPC cepstrum, as a part of an ANN based Speech Recognit...