• The Journal of the Acoustical Society of Korea
• /
• v.15 no.2
• /
• pp.40-48
• /
• 1996

In this paper, a 40 dimensional segment vector with 4 frame and 7 frame width in every monosyllable interval was compressed into a 10, 14, 20 dimensional vector using K-L expansion and neural networks, and these was used to speech recognition feature parameter for CHMM. And we also compared them with CHMM added as feature parameter to the discrete duration time, the regression coefficients and the mixture distribution. In recognition test at 100 monosyllable, recognition rates of CHMM +${\bigtriangleup}$MCEP, CHMM +MIX and CHMM +DD respectively improve 1.4%, 2.36% and 2.78% over 85.19% of CHMM. And those using vector compressed by K-L expansion are less than MCEP + ${\bigtriangleup}$MCEP but those using K-L + MCEP, K-L + ${\bigtriangleup}$MCEP are almost same. Neural networks reflect more the speech dynamic variety than K-L expansion because they use the sigmoid function for the non-linear transform. Recognition rates using vector compressed by neural networks are higher than those using of K-L expansion and other methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.12A
• /
• pp.1852-1861
• /
• 1999

In this paper, CDMA Reservation ALOHA scheme which can reduce multiple access interference and packet collision is proposed to support multi-traffic such as voice and random data with and without priority. In this scheme, the time slot is divided into two stage, access and transmission stage. Only packets with spreading codes assigned from base station in access stage can transmit their packets in transmission stage, so MAI can be reduced. To reduce packer collision in access stage, the code reservation and access permission probability are used. Code reservation is allowed for voice traffic and continuous traffic with priority using piggyback and access permission probability based on the estimation of the number of contending users in the steady-state is adaptively applied to each traffic terminal. Also, we analyzed and simulated the numerical performances required for each traffic using Markov chain modeling in a single cell environment.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.11
• /
• pp.63-71
• /
• 2003

This paper suggests the packet loss recovery method to communicate in real time in the Internet. To reduce the effects of packet loss, Forward Error Correction (FEC) that adds redundant information to voice packets can be used. Adaptive Multi Rate Wideband(AMR-WB) codec which is recently selected by the Third Generation Partnership Project(3GPP) for GSM and the third generation mobile communication WCDMA system and has also been standardized in ITU-T for providing wideband speech services is used. The major cause for speech qualitly degradation in IP-networks is packet loss. So, We recovered single lossy packet by using FEC method and concealed continued errors. The proposed scheme if evaluated in the Gilbert Internet channel model. The high quality of audio maintained up to 30% packet loss.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.1
• /
• pp.75-81
• /
• 2004

Gaussian selection (GS) is a popular approach in the continuous density hidden Markov model for fast decoding. It enables fast likelihood computation by reducing the number of Gaussian components calculated. In this paper, we propose a new GS method for the phonetic tied-mixture (PTM) hidden Markov models. The PTM model can represent each state of the same topological location with a shared set of Gaussian mixture components and contort dependent weights. Thus the proposed method imposes constraint on the weights as well as the number of Gaussian components to reduce the computational load. Experimental results show that the proposed method reduces the percentage of Gaussian computation to 16.41%, compared with 20-30% for the conventional GS methods, with little degradation in recognition.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.173-179
• /
• 2004

Due to the insufficiency of training data in large vocabulary continuous speech recognition, similar context dependent phones can be clustered by decision trees to share the data. When the decision trees are built and used to predict unseen triphones, a phonetic question set is required. The phonetic question set, which contains categories of the phones with similar co-articulation effects, is usually generated by phonetic or linguistic experts. This knowledge-based approach for generating phonetic question set, however, may reduce the homogeneity of the clusters. Moreover, the experts must adjust the question sets whenever the language or the PLU (phone-like unit) of a recognition system is changed. Therefore, we propose a data-driven method to automatically generate phonetic question set. Since the proposed method generates the phone categories using speech data distribution, it is not dependent on the language or the PLU, and may enhance the homogeneity of the clusters. In large vocabulary speech recognition experiments, the proposed algorithm has been found to reduce the error rate by 14.3%.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.603-611
• /
• 2003

This paper proposes an effective feature compensation scheme based on speech model for achieving robust speech recognition. Conventional model-based method requires off-line training with noisy speech database and is not suitable for online adaptation. In the proposed scheme, we can relax the off-line training with noisy speech database by employing the parallel model combination technique for estimation of correction factors. Applying the model combination process over to the mixture model alone as opposed to entire HMM makes the online model combination possible. Exploiting the availability of noise model from off-line sources, we accomplish the online adaptation via MAP (Maximum A Posteriori) estimation. In addition, the online channel estimation procedure is induced within the proposed framework. For more efficient implementation, we propose a selective model combination which leads to reduction or the computational complexities. The representative experimental results indicate that the suggested algorithm is effective in realizing robust speech recognition under the combined adverse conditions of additive background noise and channel distortion.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.188-194
• /
• 2014

The feature extraction mechanism of the CASA(Computational Auditory Scene Analysis) system uses time continuity and frequency channel similarity to compose a correlogram of auditory elements. In segmentation, we compose a binary mask by using cross-correlation function, mask 1(speech) has the same periodicity and synchronization. However, when there is delay between autocorrelation signals with the same periodicity, it is determined as a speech, which is considered to be a drawback. In this paper, we proposed an algorithm to improve discrimination of channel similarity using Weighted Cross-correlation in segmentation. We conducted experiments to evaluate the speech segregation performance of the CASA system in background noise(siren, machine, white, car, crowd) environments by changing SNR 5dB and 0dB. In this paper, we compared the proposed algorithm to the conventional algorithm. The performance of the proposed algorithm has been improved as following: improvement of 2.75dB at SNR 5dB and 4.84dB at SNR 0dB for background noise environment.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.106-109
• /
• 1997

For the practical isolated word recognition system, the ability to reject the out-of -vocabulary(OOV) is required. In this paper, we present a rejection method which uses the clustered phoneme modeling combined with postprocessing by likelihood ratio scoring. Our baseline speech recognition system was based on the whole-word continuous HMM. And 6 clustered phoneme models were generated using statistical method from the 45 context independent phoneme models, which were trained using the phonetically balanced speech database. The test of the rejection performance for speaker independent isolated words recogntion task on the 22 section names shows that our method is superior to the conventional postprocessing method, performing the rejection according to the likelihood difference between the first and second candidates. Furthermore, this clustered phoneme models do not require retraining for the other isolated word recognition system with different vocabulary sets.

• The Journal of the Korea Contents Association
• /
• v.5 no.2
• /
• pp.147-155
• /
• 2005

In this paper, we present a FAES(a Facial Animation with Emotion and Speech) system for speech-driven face animation with emotions. We animate face cartoons not only from input speech, but also based on emotions derived from speech signal. And also our system can ensure smooth transitions and exact representation in animation. To do this, after collecting the training data, we have made the database using SVM(Support Vector Machine) to recognize four different categories of emotions: neutral, dislike, fear and surprise. So that, we can make the system for speech-driven animation with emotions. Also, we trained on Korean young person and focused on only Korean emotional face expressions. Experimental results of our system demonstrate that more emotional areas expanded and the accuracies of the emotional recognition and the continuous speech recognition are respectively increased 7% and 5% more compared with the previous method.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.1
• /
• pp.22-32
• /
• 2003

Many of multimedia applications in distributed environments generate the packets which have the real-time characteristics for continuous audio/video data and transmit them according to the teal-time task scheduling theories. In this paper, we model the traffic for continuous media in the distributed multimedia applications based on the high-bandwidth networks and introduce the PDMA algorithm which is the hard real-time task scheduling theory for guaranteeing QoS requested by the clients. Furthermore, we propose the admission control to control the new request not to interfere the current services for maintaining the high quality of services of the applications. Since the proposed admission control is sufficient for the PDMA algorithm, the PDMA algorithm is always able to find the feasible schedule for the set of messages which satisfies it. Therefore, if the set of messages including the new request to generate the new traffic. Otherwise, it rejects the new request. In final, we present the simulation results for showing that the scheduling with the proposed admission control is of practical use.