• The Journal of the Acoustical Society of Korea
• /
• v.4 no.1
• /
• pp.9-15
• /
• 1985

In this paper, we describe a new algorithm for deciding whether a given segment of a speech signal is classified as voiced speech, unvoiced speech, or silence, based on parameters made on the signal. The measured parameters for the voiced-unvoiced classfication are the areas of each Zero crossing interval, which is given by multiplication of the magnitude by the inverse zero corssing rate of speech signals. The employed parameter for the unvoiced-silence classification, also, are each of positive area summation during four milisecond interval for the high frequency emphasized speech signals.

• Speech Sciences
• /
• v.10 no.2
• /
• pp.85-95
• /
• 2003

In speech signal processing, it is very important to detect the pitch exactly in speech recognition, synthesis and analysis. If we exactly pitch detect in speech signal, in the analysis, we can use the pitch to obtain properly the vocal tract parameter. It can be used to easily change or to maintain the naturalness and intelligibility of quality in speech synthesis and to eliminate the personality for speaker-independence in speech recognition. In this paper, we proposed a new pitch detection algorithm. First, positive center clipping is process by using the incline of speech in order to emphasize pitch period with a glottal component of removed vocal tract characteristic in time domain. And rough formant envelope is computed through peak-fitting spectrum of original speech signal infrequence domain. Using the roughed formant envelope, obtain the smoothed formant envelope through calculate the linear interpolation. As well get the flattened harmonics waveform with the algebra difference between spectrum of original speech signal and smoothed formant envelope. Inverse fast fourier transform (IFFT) compute this flattened harmonics. After all, we obtain Residual signal which is removed vocal tract element. The performance was compared with LPC and Cepstrum, ACF. Owing to this algorithm, we have obtained the pitch information improved the accuracy of pitch detection and gross error rate is reduced in voice speech region and in transition region of changing the phoneme.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.544-551
• /
• 2023

Speech enhancement used to improve the perceptual quality and intelligibility of noise speech has been studied as a method using a complex-valued spectrum that can improve both magnitude and phase in a method using a magnitude spectrum. In this paper, a study was conducted on how to apply attention mechanism to complex-valued spectrum-based speech enhancement systems to further improve the intelligibility and quality of noise speech. The attention is performed based on additive attention and allows the attention weight to be calculated in consideration of the complex-valued spectrum. In addition, the global average pooling was used to consider the importance of the feature map. Complex-valued spectrum-based speech enhancement was performed based on the Deep Complex U-Net (DCUNET) model, and additive attention was conducted based on the proposed method in the Attention U-Net model. The results of the experiments on noise speech in a living room environment showed that the proposed method is improved performance over the baseline model according to evaluation metrics such as Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short Time Object Intelligence (STOI), and consistently improved performance across various background noise environments and low Signal-to-Noise Ratio (SNR) conditions. Through this, the proposed speech enhancement system demonstrated its effectiveness in improving the intelligibility and quality of noisy speech.

• Phonetics and Speech Sciences
• /
• v.6 no.2
• /
• pp.29-34
• /
• 2014

In the Vector Taylor Series (VTS)-based noisy speech recognition methods, Hidden Markov Models (HMM) are usually trained with clean speech. However, better performance is expected by training the HMM with noisy speech. In a previous study, we could find that Minimum Mean Square Error (MMSE) estimation of the training noisy speech in the log-spectrum domain produce improved recognition results, but since the proposed algorithm was done in the log-spectrum domain, it could not be used for the HMM adaptation. In this paper, we modify the previous algorithm to derive a novel mathematical relation between test and training noisy speech in the cepstrum domain and the mean and covariance of the Multi-condition TRaining (MTR) trained noisy speech HMM are adapted. In the noisy speech recognition experiments on the Aurora 2 database, the proposed method produced 10.6% of relative improvement in Word Error Rates (WERs) over the MTR method while the previous MMSE estimation of the training noisy speech produced 4.3% of relative improvement, which shows the superiority of the proposed method.

• Journal of Audiology & Otology
• /
• v.23 no.4
• /
• pp.187-192
• /
• 2019

Background and Objectives: Clear speech is an effective communication strategy used in difficult listening situations that draws on techniques such as accurate articulation, a slow speech rate, and the inclusion of pauses. Although too slow speech and improperly amplified spectral information can deteriorate overall speech intelligibility, certain amplitude of increments of the mid-frequency bands (1 to 3 dB) and around 50% slower speech rates of clear speech, when compared to those in conversational speech, were reported as factors that can improve speech intelligibility positively. The purpose of this study was to identify whether amplitude increments of mid-frequency areas and slower speech rates were evident in Korean clear speech as they were in English clear speech. Subjects and Methods: To compare the acoustic characteristics of the two methods of speech production, the voices of 60 participants were recorded during conversational speech and then again during clear speech using a standardized sentence material. Results: The speech rate and longterm average speech spectrum (LTASS) were analyzed and compared. Speech rates for clear speech were slower than those for conversational speech. Increased amplitudes in the mid-frequency bands were evident for the LTASS of clear speech. Conclusions:The observed differences in the acoustic characteristics between the two types of speech production suggest that Korean clear speech can be an effective communication strategy to improve speech intelligibility.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.10
• /
• pp.1867-1872
• /
• 2016

In the area of digital signal processing, it is necessary to improve the quality of the speech signal after removing the background noise which exists in a various real environments. The important thing to consider when removing the background noise acoustically is that to solve the problem, depending on the information of the human auditory mechanism is mainly the amplitude spectrum of the speech signal. This paper introduces the characteristics of a frequency-weighted spectrum shaping filter for the extraction of the amplitude spectrum of the speech signal with the primary purpose. Therefore, this paper proposes an algorithm using the methods of a Wiener filter and the frequency-weighted spectrum shaping filter according to the acoustic model, after extracted the amplitude spectral information in the noisy speech signal. The spectral distortion (SD) output of the proposed algorithm is experimentally improved more than 5.28 dB compared to a conventional method.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.51-57
• /
• 1995

In this paper, we study a noise-robust feature extraction method of speech signal based on auditory modeling. The auditory model consists of a basilar membrane, a hair cell model and spectrum output stage. Basilar membrane model describes a response characteristic of membrane according to vibration in speech wave, and is represented as a band-pass filter bank. Hair cell model describes a neural transduction according to displacements of the basilar membrane. It responds adaptively to relative values of input and plays an important role for noise-robustness. Spectrum output stage constructs a mean rate spectrum using the average firing rate of each channel. And we extract feature vectors using a mean rate spectrum. Simulation results show that when auditory-based feature extraction is used, the speech recognition performance in noisy environments is improved compared to other feature extraction methods.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2E
• /
• pp.62-68
• /
• 2003

This paper addresses a novel noise-compensation scheme to solve the mismatch problem between training and testing condition for the automatic speech recognition (ASR) system, specifically in car environment. The conventional spectral subtraction schemes rely on the signal-to-noise ratio (SNR) such that attenuation is imposed on that part of the spectrum that appears to have low SNR, and accentuation is made on that part of high SNR. However, these schemes are based on the postulation that the power spectrum of noise is in general at the lower level in magnitude than that of speech. Therefore, while such postulation is adequate for high SNR environment, it is grossly inadequate for low SNR scenarios such as that of car environment. This paper proposes an efficient spectral subtraction scheme focused specifically to low SNR noisy environment by extracting harmonics distinctively in speech spectrum. Representative experiments confirm the superior performance of the proposed method over conventional methods. The experiments are conducted using car noise-corrupted utterances of Aurora2 corpus.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.1E
• /
• pp.1-10
• /
• 2008

A noise suppression algorithm is proposed for nonstationary noisy environments. The proposed algorithm is different from the conventional approaches such as the spectral subtraction algorithm and the minimum statistics noise estimation algorithm in that it classifies speech and noise signals in time-frequency bins. It calculates the ratio of the variance of the noisy power spectrum in time-frequency bins to its normalized time-frequency average. If the ratio is greater than an adaptive threshold, speech is considered to be present. Our adaptive algorithm tracks the threshold and controls the trade-off between residual noise and distortion. The estimated clean speech power spectrum is obtained by a modified gain function and the updated noisy power spectrum of the time-frequency bin. This new algorithm has the advantages of simplicity and light computational load for estimating the noise. This algorithm reduces the residual noise significantly, and is superior to the conventional methods.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3E
• /
• pp.18-24
• /
• 2001

Speaking rate represents how many phonemes in speech signal have in limited time. It is various and changeable depending on the speakers and the characters of each phoneme. The preprocessing to remove the effect of variety of speaking rate is necessary before recognizing the speech in the present speech recognition systems. So if it is possible to estimate the speaking rate in advance, the performance of speech recognition can be higher. However, the conventional speech vocoder decides the transmission rate for analyzing the fixed period no regardless of the variety rate of phoneme but if the speaking rate can be estimated in advance, it is very important information of speech to use in speech coding part as well. It increases the quality of sound in vocoder as well as applies the variable transmission rate. In this paper, we propose the method for presenting the speaking rate as parameter in speech vocoder. To estimate the speaking rate, the variety of phoneme is estimated and the Line Spectrum Pairs is used to estimate it. As a result of comparing the speaking rate performance with the proposed algorithm and passivity method worked by eye, error between two methods is 5.38% about fast utterance and 1.78% about slow utterance and the accuracy between two methods is 98% about slow utterance and 94% about fast utterances in 30 dB SNR and 10 dB SNR respectively.