• Speech Sciences
• /
• v.8 no.4
• /
• pp.59-72
• /
• 2001

In this paper, we experimented with speaker change detection that uses a statistical method for NOD (News On Demand) service. A specified speaker's change can find out content of each data in speech if analysed because it means change of data contents in news data. Speaker change detection acts as preprocessor that divide input speech by speaker. This is an important preprocessor phase for speaker tracking. We detected speaker change using GLR(generalized likelihood ratio) distance base division and BIC (Bayesian information criterion) base division among matrix method. An experiment verified speaker change point using BIC base division after divide by speaker unit using GLR distance base method first. In the experimental result, FAR (False Alarm Rate) was 63.29 in high noise environment and FAR was 54.28 in low noise environment in MDR (Missed Detection Rate) 15% neighborhood.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.7 no.1
• /
• pp.11-19
• /
• 1996

Reinke's edema is used for describing varying degrees of chronic swelling of the vocal folds. The acoustic analysis of Reinke's edema has not been reported so far in this country. The purpose of this study is to clarify acoustic and aerodynamic characteristics of the Reinke's edema. Several acoustic evaluations ＆ aerodynamic studies were done in 20 Reinke's edema patients and the data was compared with those of 20 normal controls. Videolaryngoscopy also was done to classify the severity in grading. We used C-Speech, Doctor speech science, and Phonatory function analyser. In C-Speech, we compared jitter, shimmer, and SNR(signal to noise ratio) of normal and Rrinke's edema patient. In Doctor speech science, we compared NNE(Glottal noise energy), speech fundamental frequency, voice quality between two groups. And in phonatory function analyser for aerodynamic function test, we compared speech intensity, airflow rate, and expiratory pressure between two groups. In conclusion, Reinke's edema patients showed lower voice pitches than normal, additionally jitter, shimmer, SNR(signal to noise ratio), NNE(Glottal noise energy), airflow rate, and expiratory pressure may be meaningful parameters for diagnosis and prognosis for treatment.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.4
• /
• pp.191-199
• /
• 2008

In this paper, we propose a MWF-PMC noise processing method which enhances the input speech by using Mel-warped Wiener Filtering (MWF) at pre-processing stage and compensates the recognition model by using PMC (Parallel Model Combination) at post-processing stage for speech recognition in noisy environments. The PMC uses the residual noise extracted from the silence region of enhanced speech at pre-processing stage to compensate the clean speech model and thus this method is considered to improve the performance of speech recognition in noisy environments. For recognition experiments we dew.-sampled KLE PBW (Phoneme Balanced Words) 452 word speech data to 8kHz and made 5 different SNR levels of noisy speech, i.e., 0dB. 5dB, 10dB, 15dB and 20dB, by adding Subway, Car and Exhibition noise to clean speech. From the recognition results, we could confirm the effectiveness of the proposed MWF-PMC method by obtaining the improved recognition performances over all compared with the existing combined methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.8
• /
• pp.1769-1776
• /
• 2013

In this paper, we proposed the modified YL(Yi and Loizou) algorithm, using a VAD(voice activity detector) for enhancing speech corrupted by colored noise. The performance of the proposed algorithm has been compared to the YL algorithm and LS(Lee and Son, etc.) algorithm by computer simulation. The colored noises used in the experiment were a car noise and multi-talker babble from the AURORA data base and the used voices from the TIMIT data base. It is confirmed that the proposed algorithm shows better performance from SNR(signal to noise ratio) and SSD(speech spectral distortion) viewpoint over the previous two approach.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.17 no.6
• /
• pp.154-159
• /
• 2003

In this paper, we proposed variable threshold dual rate ADPCM coding method which adapts two coding rates of the standard ADPCM of ITU G.726 for speech quality improvement at a comparably low coding rates. The ZCR(Zero Crossing Rate) is computed for speecd data and under the noisy environment, noise data dominant region showed higher ZCR and speech data dominant region showed lower ZCR. The speech data with the higher ZCR is encoded by low coding rate for reduced coded data and the speech data with the lower ZCR is encoded by high coding rate for speech quality improvements. For coded data, 2 bits are assigned for low coding rate of 16[Kbps] and 5 bits are is assigned for high coding rate of 40[Kbps]. Through the simulation, the proposed idea is evaluated and shown that the variable dual rate ADPCM coding technique shows the qood speech quality at low coding rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.4930-4951
• /
• 2018

The deep learning based speech enhancement has shown considerable success. However, it still suffers performance degradation under mismatch conditions. In this paper, an adaptation method is proposed to improve the performance under noise mismatch conditions. Firstly, we advise a noise aware training by supplying identity vectors (i-vectors) as parallel input features to adapt deep neural network (DNN) acoustic models with the target noise. Secondly, given a small amount of adaptation data, the noise-dependent DNN is obtained by using $L_2$ regularization from a noise-independent DNN, and forcing the estimated masks to be close to the unadapted condition. Finally, experiments were carried out on different noise and SNR conditions, and the proposed method has achieved significantly 0.1%-9.6% benefits of STOI, and provided consistent improvement in PESQ and segSNR against the baseline systems.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.3
• /
• pp.252-261
• /
• 2013

The common speech recognition system displays higher recognition performance in a quiet environment, while its performance declines sharply in a real environment where there are noises. To implement a speech recognizer that is robust in different speech settings, this study suggests the method of Parallel Model Combination adaptation using frequency-variant based on environment-awareness (FV-PMC), which uses variants in frequency; acquires the environmental data for speech recognition; applies it to upgrading the speech recognition model; and promotes its performance enhancement. This FV-PMC performs the speech recognition with the recognition model which is generated as followings: i) calculating the average frequency variant in advance among the readily-classified noise groups and setting it as a threshold value; ii) recalculating the frequency variant among noise groups when speech with unknown noises are input; iii) regarding the speech higher than the threshold value of the relevant group as the speech including the noise of its group; and iv) using the speech that includes this noise group. When noises were classified with the proposed FV-PMC, the average accuracy of classification was 56%, and the results from the speech recognition experiments showed the average recognition rate of Set A was 79.05%, the rate of Set B 79.43%m, and the rate of Set C 83.37% respectively. The grand mean of recognition rate was 80.62%, which demonstrates 5.69% more improved effects than the recognition rate of 74.93% of the existing Parallel Model Combination with a clear model, meaning that the proposed method is effective.

• Speech Sciences
• /
• v.13 no.1
• /
• pp.129-139
• /
• 2006

In this paper, we propose two effective energy feature normalization methods for robust speech recognition in noisy environments. In the first method, we estimate the noise energy and remove it from the noisy speech energy. In the second method, we propose a modified algorithm for the Log-energy Dynamic Range Normalization (ERN) method. In the ERN method, the log energy of the training data in a clean environment is transformed into the log energy in noisy environments. If the minimum log energy of the test data is outside of a pre-defined range, the log energy of the test data is also transformed. Since the ERN method has several weaknesses, we propose a modified transform scheme designed to reduce the residual mismatch that it produces. In the evaluation conducted on the Aurora2.0 database, we obtained a significant performance improvement.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.4
• /
• pp.555-560
• /
• 2013

This paper first proposes a classification algorithm which detects a voiced, unvoiced, and silence signal using distance measure, logarithm power and root mean square methods at each frame, then a spectrum subtraction algorithm based on a subband filter. The proposed algorithm subtracts spectrums of white noise and street noise from noisy signal based on the subband filter at each frame. In this experiment, experimental results of the proposed spectrum subtraction algorithm demonstrate using the speech and noise data of Aurora-2 database. Based on measuring the speech-to-noise ratio (SNR), experiments confirm that the proposed algorithm is effective for the speech by contaminated the noise. From the experiments, the improvement in the output SNR values was approximately 2.1 dB and 1.91 dB better for white noise and street noise, respectively.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.198-202
• /
• 1988

In digital mobile communications received speech data are affected by burst errors as well as random errors. To overcome these errors we propose a bit-selective forward error correction scheme for the speech data which is sub-band coded at 13 kbps and transmitted over a 16 kbps channel. For a few error correcting codes the signal-to-noise ratio of error-corrected speech is obtained and compared through the simulation of mobile communication channels.