• Journal of Biomedical Engineering Research
• /
• v.31 no.6
• /
• pp.417-426
• /
• 2010

We present a speech processing strategy incorporating instantaneous frequency (IF) encoding for the enhancement of melody recognition performance of cochlear implants. For the IF extraction from incoming sound, we propose the use of a Teager energy operator (TEO), which is advantageous for its lower computational load. From time-frequency analysis, we verified that the TEO-based method provides proper IF encoding of input sound, which is crucial for melody recognition. Similar benefit could be obtained also from the use of a Hilbert transform (HT), but much higher computational cost was required. The melody recognition performance of the proposed speech processing strategy was compared with those of a conventional strategy using envelope extraction, and the HT-based IF encoding. Hearing tests on normal subjects were performed using acoustic simulation and a musical contour identification task. Insignificant difference in melody recognition performance was observed between the TEO-based and HT-based IF encodings, and both were superior to the conventional strategy. However, the TEO-based strategy was advantageous considering that it was approximately 35% faster than the HT-based strategy.

• ETRI Journal
• /
• v.32 no.3
• /
• pp.395-405
• /
• 2010

A novel multiclassifier system (MCS) strategy is proposed and applied to a text-dependent speaker verification task. The presented scheme optimizes the linear combination of classifiers on an on-line basis. In contrast to ordinary MCS approaches, neither a priori distributions nor pre-tuned parameters are required. The idea is to improve the most accurate classifier by making use of the incremental information provided by the second classifier. The on-line multiclassifier optimization approach is applicable to any pattern recognition problem. The proposed method needs neither a priori distributions nor pre-estimated weights, and does not make use of any consideration about training/testing matching conditions. Results with Yoho database show that the presented approach can lead to reductions in equal error rate as high as 28%, when compared with the most accurate classifier, and 11% against a standard method for the optimization of linear combination of classifiers.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.42-47
• /
• 1994

A pitch detector is an essential component in a variety of speech processing systems. Besides providing valuable insights into the nature of the exciation source for speech production, the pitch contour of an utterance is useful for recognizing speakers, aids-to-the handicapped, and is required in almost all speech analysis-synthesis system. Because of the importance of the pitch detection, a wide variety algorithms for pitch detection have been proposed in speech procesing literature. Thus, in this paper we discuss th evarious type of pitch detection algorithms which have been proposed until now. Then we provide th eperformance measurements for seven pitch detection algorithms.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1992.06a
• /
• pp.49-53
• /
• 1992

In many applications such as speech analysis, speech coding, speech recognition, etc., the voiced-unvoiced decision should be performed correctly for efficient processing. One of the parameters which are used for voice-unvoiced decision is zero-crossing. But the information of higher formants have not represented as the zero-crossing rate for higher formants of speech signals.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.603-606
• /
• 1998

In a large number of words and the continued speech recognition system using a phoneme as teh recognition unit, it is necessary to segment processing. In this paper, a normalized AMDF new method. The suggested parameter represents a degree of sharpness at valley point. This method can detect the speech segment between the steady state and transient region to the continued speech without a prior information of speech signal.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.3E
• /
• pp.85-90
• /
• 2004

This paper presents two kinds of new approaches, one of which is concerned with recognition of emotional speech such as anger, happiness, normal, sadness, or surprise. The other is concerned with emotion recognition in speech. For the proposed speech recognition system handling human speech with emotional states, total nine kinds of prosodic features were first extracted and then given to prosodic identifier. In evaluation, the recognition results on emotional speech showed that the rates using proposed method increased more greatly than the existing speech recognizer. For recognition of emotion, on the other hands, four kinds of prosodic parameters such as pitch, energy, and their derivatives were proposed, that were then trained by discrete duration continuous hidden Markov models(DDCHMM) for recognition. In this approach, the emotional models were adapted by specific speaker's speech, using maximum a posteriori(MAP) estimation. In evaluation, the recognition results on emotional states showed that the rates on the vocal emotions gradually increased with an increase of adaptation sample number.

• Proceedings of the KSPS conference
• /
• 2005.11a
• /
• pp.13-16
• /
• 2005

As language learning that utilizes speech and information processing technology is getting popular. Speech Information Technology & Promotion Center(SiTEC) has created and is distributing speech corpora for STiLL in order to support basic research and development of products. We will introduce the corpus for Korean and those for English which we have created and are distributing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.9
• /
• pp.1673-1678
• /
• 2016

In the area of the speech recognition processing, background noises are caused the incorrect response to the speech input, therefore the speech recognition rates are decreased by the background noises. Accordingly, a more high level noise processing techniques are required since these kinds of noise countermeasures are not simple. Therefore, this paper proposes an algorithm to distinguish between the stationary background noises or non-stationary background noises and the speech signal having short time duration in the noisy environments. The proposed algorithm uses the characteristic parameter of the improved speech signal as an important measure in order to distinguish different types of the background noises and the speech signals. Next, this algorithm estimates various kinds of the background noises using a multi-layer perceptron neural network. In this experiment, it was experimentally clear the estimation of the background noises and the speech signals.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.8
• /
• pp.1665-1674
• /
• 2011

In this paper, we proposed an algorithm for speech enhancement of speeches corrupted by colored noise. When there is no correlation between colored noise and speech signal, the colored noise turns into white noise through whitening transformation. This transformed signal has been applied to the generalized subspace approach for speech enhancement. The speech spectral distortion, produced by the whitening transformation as pre-processing, has been restored by using the inverse whitening transformation as post-processing of the proposed algorithm. The performance of the proposed algorithm for speech enhancement has been confirmed by computer simulation. The colored noises used in this experiment were car noise and multi-talker babble. It is confirmed that the proposed algorithm shows better performance from SNR and SSD viewpoint over the previous approach with the data from the AURORA and TIMIT data base.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.413-416
• /
• 2002

In this paper, a speech enhancement system using microphone array with adaptive Post-Processing is implemented in real-lime with TMS320C6201 DSP. It consists of delay-and-sum beamformer and adaptive post-processing filters with NLMS (Normalized Least Mean Square) algorithm. THS1206 ADC is used for collection of 4-channel microphone signals. Sizes of program memory, data ROM and data RAM of the implemented system are 15,744, 748 and 47,540 bytes, respectively. Finally 21.839${\times}$106 clocks per second is required for real-time operation.