• The Journal of the Acoustical Society of Korea
• /
• v.17 no.4E
• /
• pp.11-16
• /
• 1998

For large vocabulary speech recognition using HMMs, context-dependent subword units have been often employed. However, when context-dependent phone models are used, they result in a system which has too may parameters to train. The problem of too many parameters and too little training data is absolutely crucial in the design of a statistical speech recognizer. Furthermore, when building large vocabulary speech recognition systems, unseen triphone problem is unavoidable. In this paper, we propose the modified phonetic decision tree algorithm for the automatic prediction of unseen triphones which has advantages solving these problems through following two experiments in Japanese contexts. The baseline experimental results show that the modified tree based clustering algorithm is effective for clustering and reducing the number of states without any degradation in performance. The task experimental results show that our proposed algorithm also has the advantage of providing a automatic prediction of unseen triphones.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1991.06a
• /
• pp.15-20
• /
• 1991

In a text-to-speech system, sound units (e. q., phonemes, words, or phrases) can be concatenated together to produce required utterance. The quality of the resulting speech is dependent on factors including the phonological/prosodic contour, the quality of basic concatenation units, and how well the units join together. Thus although the quality of each basic sound unit is high, if occur the discontinuity in the concatenation part then the quality of synthesis speech is decrease. To solve this problem, a smoothing operation should be carried out in concatenation parts. But a major problem is that, as yet, no method of parameter smoothing is availalbe for joining the segment together.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.5
• /
• pp.2588-2609
• /
• 2019

Speech homomorphic encryption has become one of the key components in secure speech storing in the public cloud computing. The major problem of speech homomorphic encryption is the huge data expansion of speech cipher-text. To address the issue, this paper presents a speech homomorphic encryption scheme with less data expansion, which is a probabilistic statistics and addition homomorphic cryptosystem. In the proposed scheme, the original digital speech with some random numbers selected is firstly grouped to form a series of speech matrix. Then, a proposed matrix encryption method is employed to encrypt that speech matrix. After that, mutual information in sample speech cipher-texts is reduced to limit the data expansion. Performance analysis and experimental results show that the proposed scheme is addition homomorphic, and it not only resists statistical analysis attacks but also eliminates some signal characteristics of original speech. In addition, comparing with Paillier homomorphic cryptosystem, the proposed scheme has less data expansion and lower computational complexity. Furthermore, the time consumption of the proposed scheme is almost the same on the smartphone and the PC. Thus, the proposed scheme is extremely suitable for secure speech storing in public cloud computing.

• Transactions on Control, Automation and Systems Engineering
• /
• v.2 no.1
• /
• pp.7-12
• /
• 2000

A new speech enhancement algorithm for speech corrupted by slowly varying additive colored noise is suggested based on a state-space signal model. Due to the FIR structure and the unimportance of long-term past information, the receding horizon (RH) FIR filter known to be a best linear unbiased estimation (BLUE) filter is utilized in order to obtain noise-suppressed speech signal. As a special case of the colored noise problem, the suggested approach is generalized to perform the single blind signal separation of two speech signals. It is shown that the exact speech signal is obtained when an incoming speech signal is noise-free.

• MALSORI
• /
• no.67
• /
• pp.195-216
• /
• 2008

This paper addresses the problem of single-channel speech separation to extract the speech signal uttered by the speaker of interest from a mixture of speech signals. We propose to apply time-frequency smoothing to the existing statistical single-channel speech separation algorithms: The soft mask and the minimum-mean-square-error (MMSE) algorithms. In the proposed method, we use the two smoothing later. One is the uniform mask filter whose filter length is uniform at the time-Sequency domain, and the other is the met-scale filter whose filter length is met-scaled at the time domain. In our speech separation experiments, the uniform mask filter improves speaker-to-interference ratio (SIR) by 2.1dB and 1dB for the soft mask algorithm and the MMSE algorithm, respectively, whereas the mel-scale filter achieves 1.1dB and 0.8dB for the same algorithms.

• ETRI Journal
• /
• v.25 no.1
• /
• pp.49-51
• /
• 2003

Pitch estimation is important in various speech research areas, but when the speech is noisy, accurate pitch estimation with conventional pitch detectors is almost impossible. To solve this problem, we propose a new pitch detection algorithm for noisy speech using a noise whitening technique on the background noise and obtain successful results.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.216-218
• /
• 2005

This paper present a new approach to a noise robust recognizer for WPS interface. In noisy environments, performance of speech recognition is decreased rapidly. To solve this problem, We propose the recognition system using vocal-cord signal instead of speech. Vocal-cord signal has low quality but it is more robust to environment noise than speech signal. As a result, we obtained 75.21% accuracy using MFCC with CMS and 83.72% accuracy using ZCPA with RASTA.

• Journal of Korea Multimedia Society
• /
• v.16 no.8
• /
• pp.905-913
• /
• 2013

The Parallel Model Compensation Using Frequency-variant: FV-PMC for noise-robust speech recognition is a method to classify the noises, which are expected to be intermixed with input speech when recognized, into several groups of noises by setting average frequency variant as a threshold value; and to recognize the noises depending on the classified groups. This demonstrates the excellent performance considering noisy speech categorized as good using the standard threshold value. However, it also holds a problem to decrease the average speech recognition rate with regard to unclassified noisy speech, for it conducts the process of speech recognition, combined with noiseless model as in the existing PMC. To solve this problem, this paper suggests a enhanced method of recognition to prevent the unclassified through improving the extent of rating scales with use of maximum likelihood so that the noise groups, including input noisy speech, can be classified into more specific groups, which leads to improvement of the recognition rate. The findings from recognition experiments using Aurora 2.0 database showed the improved results compared with those from the method of the previous FV-PMC.

• MALSORI
• /
• no.61
• /
• pp.63-74
• /
• 2007

Discrimination of music and speech from the multimedia signal is an important task in audio coding and broadcast monitoring systems. This paper deals with the problem of feature parameter extraction for discrimination of music and speech. The wavelet transform is a multi-resolution analysis method that is useful for analysis of temporal and spectral properties of non-stationary signals such as speech and audio signals. We propose new feature parameters extracted from the wavelet transformed signal for discrimination of music and speech. First, wavelet coefficients are obtained on the frame-by-frame basis. The analysis frame size is set to 20 ms. A parameter $E_{sum}$ is then defined by adding the difference of magnitude between adjacent wavelet coefficients in each scale. The maximum and minimum values of $E_{sum}$ for period of 2 seconds, which corresponds to the discrimination duration, are used as feature parameters for discrimination of music and speech. To evaluate the performance of the proposed feature parameters for music and speech discrimination, the accuracy of music and speech discrimination is measured for various types of music and speech signals. In the experiment every 2-second data is discriminated as music or speech, and about 93% of music and speech segments have been successfully detected.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.30 no.5
• /
• pp.447-456
• /
• 2008

There is close relationship between intraoral structural anomaly and speech- functional problem. Patient with cleft palate patients & ankyloglossia is a typical example, patients with structural anomaly is repaired toward normal structure by operation. Ankyloglossia may cause functional limitation even after adequate surgical treatment speech disorders being one of them. Interindividually, they vary a lot, showing typical articulation specifics. The objective of this study was to evaluate and compare speech for children with ankyloglossia and general public, to determine whether ankyloglossia is associated with articulation problem. We wanted to present criteria for indication of frenectomy. The group of subject is composed of 10 childrens with ankyloglossia and articulation problem, visited the Oral and Maxillofacial surgical unit, dental hospital, Chonbuk university. The average age is 5 Y 7M, M : F ratio is 8 : 2 at the time of speech test. Control group is composed of 10 members without oral structural anomaly. The average age is 5 Y 10M, M : F ratio is 3 : 7 at the time of speech test. Outcomes were measured the PPVT(Peabody Picture Vocabulary Test), PCAT(Picture Consonant Articulation Test), Nasometer II test result obtained each group, statistically measured by Mann-whitney's U Test. There was no difference for 'chronological age-age equivalent' between two group. There was significant difference for 'consonant accuracy' between two group, showed more lower scores in subject group. There was more 'consonant error' in subject group, mostly showed/1/,/s/. A major modality of 'consonant error' was mostly distortion and replacement. There was no significant difference between two group for nasality.