Hindi phoneme classification using Wiener filtered wavelet packet decomposed periodic and aperiodic acoustic feature

Biswas, Amit; Sahu, Prasanna Kumar; Bhowmick, Anirban; Chandra, Mahesh

doi:10.1016/j.compeleceng.2014.12.017

Cited by 16 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The wavelet transforms effectively do the time-frequency analysis in the case of the non-stationary or quasistationary signal [4]. Wavelet packets (WP) [3,26] shows their importance in signal representation schemes such as speech analysis [9].…”

Section: Wavelet Packet Based Erb Cepstral Features (Werbc)mentioning

confidence: 99%

“…Some amount of research has been done by [9,16,21,38,39,45] in Hindi speech recognition using wavelet transformation. The WERBC feature extraction technique is proposed in 2014 [4]. The process of converting the speech signal into WERBC features via admissible wavelet packet transform is shown in Figure 1.…”

Section: Wavelet Packet Based Erb Cepstral Features (Werbc)mentioning

confidence: 99%

See 1 more Smart Citation

Discriminatively trained continuous Hindi speech recognition using integrated acoustic features and recurrent neural network language modeling

Kumar

Aggarwal

2020

Journal of Intelligent Systems

View full text Add to dashboard Cite

This paper implements the continuous Hindi Automatic Speech Recognition (ASR) system using the proposed integrated features vector with Recurrent Neural Network (RNN) based Language Modeling (LM). The proposed system also implements the speaker adaptation using Maximum-Likelihood Linear Regression (MLLR) and Constrained Maximum likelihood Linear Regression (C-MLLR). This system is discriminatively trained by Maximum Mutual Information (MMI) and Minimum Phone Error (MPE) techniques with 256 Gaussian mixture per Hidden Markov Model(HMM) state. The training of the baseline system has been done using a phonetically rich Hindi dataset. The results show that discriminative training enhances the baseline system performance by up to 3%. Further improvement of ~7% has been recorded by applying RNN LM. The proposed Hindi ASR system shows significant performance improvement over other current state-of-the-art techniques.

show abstract

Section: Wavelet Packet Based Erb Cepstral Features (Werbc)mentioning

confidence: 99%

Section: Wavelet Packet Based Erb Cepstral Features (Werbc)mentioning

confidence: 99%

Discriminatively trained continuous Hindi speech recognition using integrated acoustic features and recurrent neural network language modeling

Kumar

Aggarwal

2020

Journal of Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…Biswas et al [3] discussed about wavelet packet acoustic features that are found to be very promising in unvoiced phoneme classification tasks, but they are less effective in capturing periodic information from voiced speech. This motivated them to develop a wavelet packet-based feature extraction technique that signifies both the periodic and aperiodic information.…”

Section: Related Workmentioning

confidence: 99%

Noise Reduction Using Modified Wiener Filter in Digital Hearing Aid for Speech Signal Enhancement

Kumar¹,

Chari²

2019

Journal of Intelligent Systems

View full text Add to dashboard Cite

AbstractSpeech signals are usually affected by noises during the communication process. For suppressing the noise signal that is combined with the speech signal, a Wiener filter is adapted in digital hearing aids. Weiner filter plays an important role in noise suppression and enhancement by estimating the relation between the power spectra of the noise-affected speech signal and the noise signal. Power consumption and the hardware requirement are the important problems in adapting Weiner filter for major communication systems. In this work, we implemented an efficient Wiener filter and applied it for noise suppression along with a real-valued fast Fourier transform (FFT)/real-valued inverse FFT processor in digital hearing aids. The pipelined process was adopted for increasing the performance of the system. The proposed Wiener filter was designed to remove the iteration problems in the conventional Wiener filter. The division operation was replaced by an efficient inverse and multiplication operation in the proposed design. A modified architecture for matrix inversion with low computation complexity was implemented. The complete design computation was based on IEEE-754 standard single-precision floating-point numbers. The Wiener filter and the whole system architecture was implemented and designed on a Field Programmable Gate Array platform and simulated to validate the results in Xilinx ISE tools. An efficient reduction in power and area was obtained by adapting the proposed method for speech signal noise degradation. The performance of the proposed design was found to be 50.01% more efficient than that of existing designs.

show abstract

“…It has been noted that generally most of the energy of vowel lies below 2 kHz and in case of voiced consonants lies below 3 kHz as shown in Fig. 1 [18]. Vowels are lower‐frequency components of speech and create the sound volume of speech.…”

Section: Introductionmentioning

confidence: 99%

Admissible wavelet packet sub‐band‐based harmonic energy features for Hindi phoneme recognition

Biswas¹,

Sahu²,

Bhowmick³

et al. 2015

IET signal process.

Self Cite

View full text Add to dashboard Cite

In recent years wavelet packet (WP) transform has been used as an important speech representation tool. WP based acoustic features have found to be more effective than the short time Fourier transform (STFT) based features to capture the information of unvoiced phoneme in continuous speech. But wavelet features fail to carry the same usefulness to represent the voiced phonemes such as vowels, nasals. This paper proposes a new WP sub-band based features by taking care of harmonic information of voiced speech signal. It has been noticed that most of the voiced energy of the speech signal lies in between 250Hz-2000Hz. Thus the proposed technique emphasizes the individual sub-band harmonic energy upto 2 kHz. The speech signal is decomposed into 16 wavelet sub-bands and Harmonic energy features (HEF) are combined with wavelet packet cepstral features (WPCC). More in IET Signal Processing Digital Library

show abstract

Hindi phoneme classification using Wiener filtered wavelet packet decomposed periodic and aperiodic acoustic feature

Cited by 16 publications

References 23 publications

Discriminatively trained continuous Hindi speech recognition using integrated acoustic features and recurrent neural network language modeling

Discriminatively trained continuous Hindi speech recognition using integrated acoustic features and recurrent neural network language modeling

Noise Reduction Using Modified Wiener Filter in Digital Hearing Aid for Speech Signal Enhancement

Admissible wavelet packet sub‐band‐based harmonic energy features for Hindi phoneme recognition

Contact Info

Product

Resources

About