• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.40-42
• /
• 2009

This paper presents an algorithm, which is based on Otsu's method, for accurate and robust endpoint detection for speech recognition under noisy environments. The features are extracted in time domain, and then an optimal threshold is selected by minimizing the discriminant criterion, so as to maximize the separability of the speech part and environment part. The simulation results show that the method play a good performance in detection accuracy.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.4
• /
• pp.178-183
• /
• 2006

As a lot of researches on the speech signal processing are performed due to the recent rapid development of the information-communication technology. the pitch period is used as an important element to various speech signal application fields such as the speech recognition. speaker identification. speech analysis. or speech synthesis. A variety of algorithms for the time and the frequency domains related with such pitch period detection have been suggested. One of the pitch detection algorithms for the time domain. AMDF (average magnitude difference function) uses distance between two valley points as the calculated pitch period. However, it has a problem that the algorithm becomes complex in selecting the valley points for the pitch period detection. Therefore, in this paper we proposed the modified AMDF(M-AMDF) algorithm which recognizes the entire minimum valley points as the pitch period of the speech signal by using the rotation transform of AMDF. In addition, a threshold is set to the beginning portion of speech so that it can be used as the selection criteria for the pitch period. Moreover the proposed algorithm is compared with the conventional ones by means of the simulation, and presents better properties than others.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.5
• /
• pp.5-12
• /
• 1996

We propose a two-channel(Speech & EGG) pitch detection algorithm. The EGG signal monitors the vibratory motion of vocal folds very well. Therefore, using the EGG signal as well as speech signal, we obtain a reliable and robust pitch detection algorithm that minimizers problems occuring in the pitch detection with speech only. The proposed algorithm gives precise pitch markers that are synchronized to the speech in the time domain. Experimental results demonstrate the superiority of the two-channel pitch detection algorithm over the conventional method, and it can be used in obtaining reference pitch for evaluation of other pitch detection algorithms.

• 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.

• Proceedings of the KSPS conference
• /
• 2003.10a
• /
• pp.29-32
• /
• 2003

This paper proposes an automatic pronunciation correction system which provides users with correction guidelines for each pronunciation error. For this purpose, we develop an HMM speech recognizer which automatically classifies pronunciation errors when Korean speaks foreign language. And, we collect speech database of native and nonnative speakers using phonetically balanced word lists. We perform analysis of mispronunciation types from the experiment of automatic mispronunciation detection using speech recognizer.

• Speech Sciences
• /
• v.10 no.1
• /
• pp.95-105
• /
• 2003

This paper describes a new parameter for voice activity detection which serves as a front-end part for automatic speech recognition systems. The new parameter called run-ratio is derived from the runs test statistic which is used in the statistical test for randomness of a given sequence. The run-ratio parameter has the property that the values of the parameter for the random sequence are about 1. To apply the run-ratio parameter into the voice activity detection method, it is assumed that the samples of an inputted audio signal should be converted to binary sequences of positive and negative values. Then, the silence region in the audio signal can be regarded as random sequences so that their values of the run-ratio would be about 1. The run-ratio for the voiced region has far lower values than 1 and for fricative sounds higher values than 1. Therefore, the parameter can discriminate speech signals from the background sounds by using the newly derived run-ratio parameter. The proposed voice activity detector outperformed the conventional energy-based detector in the sense of error mean and variance, small deviation from true speech boundaries, and low chance of missing real utterances

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.2
• /
• pp.73-79
• /
• 2011

This paper presents a new impulsive noise detection algorithm in speech signal. The proposed method employs the frequency domain characteristic of the impulsive noise to improve the detection accuracy while avoiding the false-alarm problem by the pitch of the speech signal. Furthermore, we proposed time-frequency domain impulsive noise detector that utilizes both the time and frequency domain parameters which minimizes the false-alarm problem by mutually complementing each other. As the result, the proposed time-frequency domain detector shows the best performance with 99.33 % of detection accuracy and 1.49 % of false-alarm rate.

• Phonetics and Speech Sciences
• /
• v.7 no.4
• /
• pp.35-40
• /
• 2015

We propose a speech waveform forgery detection algorithm based on the flatness of frequency distribution. We devise a new measure of flatness which emphasizes the local change of the frequency distribution. Our measure calculates the sum of the differences between the energies of neighboring frequency bands. We compare the proposed measure with conventional flatness measures using a set of a large amount of test sounds. We also compare- the proposed method with conventional detection algorithms based on spectral distances. The results show that the proposed method gives lower equal error rate for the test set compared to the conventional methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.4
• /
• pp.276-280
• /
• 2016

A fixed rate speech coder based on the filter bank and the non-uniform sampling technique is proposed. The non-uniform sampling is achieved by the detection of inflection points (IPs). A speech block is band passed by the filter bank, and the subband signals are processed by the IP detector, and the detected IP patterns are compared with entries of the IP database. For each subband signal, the address of the closest member of the database and the energy of the IP pattern are transmitted through channel. In the receiver, the decoder recovers the subband signals using the received addresses and the energy information, and reconstructs the speech via the filter bank summation. As results, the coder shows fixed data rate contrary to the existing speech coders based on the non-uniform sampling. Through computer simulation, the usefulness of the proposed technique is confirmed. The signal-to-noise ratio (SNR) performance of the proposed method is comparable to that of the uniform sampled pulse code modulation (PCM) below 20 kbps data rate.

• Phonetics and Speech Sciences
• /
• v.10 no.3
• /
• pp.19-29
• /
• 2018

We propose to use independent component analysis (ICA) and deep neural network (DNN) to detect music sections in broadcast drama contents. Drama contents mainly comprise silence, noise, speech, music, and mixed (speech+music) sections. The silence section is detected by signal activity detection. To detect the music section, we train noise, speech, music, and mixed models with DNN. In computer experiments, we used the MUSAN corpus for training the acoustic model, and conducted an experiment using 3 hours' worth of Korean drama contents. As the mixed section includes music signals, it was regarded as a music section. The segmentation error rate (SER) of music section detection was observed to be 19.0%. In addition, when stereo mixed signals were separated into music signals using ICA, the SER was reduced to 11.8%.