• 한국정보통신설비학회:학술대회논문집
• /
• 2007.08a
• /
• pp.354-358
• /
• 2007

This article presents several methods of mobile communication network to access technologies utilizing unlicensed spectrum interworking. Generic Access Network (GAN) technology was already specified in GERAN (GSM EDGE Radio Access Network) and Interworking WLAN (I-WLAN) was standardized for WCDMA system for WLAN user to access WCDMA packet based services through WLAN access point. Voice Call Continuity is not access network dependent technology but is a kind of domain change scheme for voice call from Circuit Switching (CS) network to IP Multimedia Subsystem (IMS) and vice versa.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.4
• /
• pp.991-998
• /
• 2010

In realization of wireless home network system using speech recognition in indoor voice recognition environment, background noise and reverberation are two main causes of digression in voice recognition system. In this study, the home network system resistant to reverberation and background noise using voice section detection method based on spectral entropy in indoor recognition environment is to be realized. Spectral subtraction can reduce the effect of reverberation and remove noise independent from voice signal by eliminating signal distorted by reverberation in spectrum. For effective spectral subtraction, the correct separation of voice section and silent section should be accompanied and for this, improvement of performance needs to be done, applying to voice section detection method based on entropy. In this study, experimental and indoor environment testing is carried out to figure out command recognition rate in indoor recognition environment. The test result shows that command recognition rate improved in static environment and reverberant room condition, using voice section detection method based on spectral entropy.

• Journal of Internet Computing and Services
• /
• v.24 no.2
• /
• pp.11-18
• /
• 2023

Recently, in the field of Speech Emotion Recognition (SER), many studies have been conducted to improve accuracy using voice features and modeling. In addition to modeling studies to improve the accuracy of existing voice emotion recognition, various studies using voice features are being conducted. This paper, voice files are separated by time interval in a time series method, focusing on the fact that voice emotions are related to time flow. After voice file separation, we propose a model for classifying emotions of speech data by extracting speech features Mel, Chroma, zero-crossing rate (ZCR), root mean square (RMS), and mel-frequency cepstrum coefficients (MFCC) and applying them to a recurrent neural network model used for sequential data processing. As proposed method, voice features were extracted from all files using 'librosa' library and applied to neural network models. The experimental method compared and analyzed the performance of models of recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU) using the Interactive emotional dyadic motion capture Interactive Emotional Dyadic Motion Capture (IEMOCAP) english dataset.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.26-30
• /
• 2019

This paper proposes a new voice activity detection (VAD) method which is based on SNR and non-intrusive speech intelligibility estimation. In the conventional SNR-based VAD methods, voice activity probability is obtained by estimating frame-wise SNR at each spectral component. However these methods lack performance in various noisy environments. We devise a hybrid VAD method that uses non-intrusive speech intelligibility estimation as well as SNR estimation, where the speech intelligibility score is estimated based on deep neural network. In order to train model parameters of deep neural network, we use MFCC vector and the intrusive speech intelligibility score, STOI (Short-Time Objective Intelligent Measure), as input and output, respectively. We developed speech presence measure to classify each noisy frame as voice or non-voice by calculating the weighted average of the estimated STOI value and the conventional SNR-based VAD value at each frame. Experimental results show that the proposed method has better performance than the conventional VAD method in various noisy environments, especially when the SNR is very low.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.512-517
• /
• 2018

Improving voice quality is a major concern in telecommunications. In this paper, we propose a robust speech quality enhancement against background noise and packet loss at VoIP (Voice-over-IP) receiver. The proposed method combines network jitter estimation based on hybrid Markov chain, adaptive playout scheduling using the estimated jitter, and speech enhancement based on restoration of amplitude and phase to enhance the quality of the speech signal arriving at the VoIP receiver over IP network. The experimental results show that the proposed method removes the background noise added to the speech signal before encoding at the sender side and provides the enhanced speech quality in an unstable network environment.

• Phonetics and Speech Sciences
• /
• v.12 no.3
• /
• pp.55-63
• /
• 2020

Voice conversion can be applied to various voice processing applications. It can also play an important role in data augmentation for speech recognition. The conventional method uses the architecture of voice conversion with speech synthesis, with Mel filter bank as the main parameter. Mel filter bank is well-suited for quick computation of neural networks but cannot be converted into a high-quality waveform without the aid of a vocoder. Further, it is not effective in terms of obtaining data for speech recognition. In this paper, we focus on performing voice-to-voice conversion using only the raw spectrum. We propose a deep learning model based on the transformer network, which quickly learns the voice conversion properties using an attention mechanism between source and target spectral components. The experiments were performed on TIDIGITS data, a series of numbers spoken by an English speaker. The conversion voices were evaluated for naturalness and similarity using mean opinion score (MOS) obtained from 30 participants. Our final results yielded 3.52±0.22 for naturalness and 3.89±0.19 for similarity.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.14 no.4
• /
• pp.360-368
• /
• 1989

In this paper, the performance of an integrated voice/data cut-through switching network is studied. We first derive cut-through probabilities of voice and data packets at intermediate nodes. Then, the Laplace transform for the network delay is obtained. According to numerical results, the performance of cut-through switching is superior to that of packet switching for integrated voice/data networks.

• The KIPS Transactions:PartC
• /
• v.15C no.5
• /
• pp.367-374
• /
• 2008

To realize the voice privacy between CDMA mobile phone and PSTN terminal, the voice frames shall be transmitted transparently between the heterogeneous networks. For satisfying this requirement, we propose the method which transmits voice frames using the CDMA circuit data channel in real time. In this paper we analyze the causes of voice delay which occurs during voice transmission using circuit data channel. And in order to overcome this kind of delay, the technique controlling the TCP control flag and the variable audio block construction algorithm according to the vocoder output rate are proposed. As a result of experimenting by applying the proposed method, we confirmed that the transit delay was improved with about average 70%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.1
• /
• pp.92-100
• /
• 2016

It is informed that the Voice over LTE(VoLTE) which serves voice and message on IP networks is better in terms of economies of scale than the legacy voice service on 2G/3G circuit-switched networks because of its technological and cost efficiency. In addition, services of voice and data are running on a single LTE network and as a result VoLTE has the more economies of scope. But, there is no study about how much technology-efficiency VoLTE has compared to circuit-based voice service and how much voice charge can be reduced as VoLTE grows up. This paper analyzes empirically cost-efficiency of VoLTE against circuit-based voice service and quantifies the reduction of voice charge as 2G/3G voice traffic shifts to VoLTE. The results describe the first is that the average cost of the total voice traffic rises shortly just after the investment of LTE network for providing VoLTE but it will soon have a capacity available to reduce the charge due to VoLTE's outstanding cost efficiency on the assumption that voice traffic is fixed, and the second is that the charge can be cut to 60% of the current rate in case of all the voice traffic moves to VoLTE. The latter proves partially the validation of data-focusing pricing plan. Our results are expected to become basic data for network operators' establishing pricing strategies and for policy makers' inducing price cutting.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.346-353
• /
• 2021

In this proposal, we aim to enhance the security of systems accounts by improving the authentication techniques. We mainly intend to enhance the accuracy of the one-time passwords via including voice biometric and recognition techniques. The recognition will be performed on the server to avoid redirecting voice signatures by hackers. Further, to enhance the privacy of data and to ensure that the active user is legitimate, we propose to periodically update the activated sessions using a user-selected biometric factor. Finally, we recommend adding a pre-transaction re-authentication which will guarantee enhanced security for sensitive operations. The main novelty of this proposal is the use of the voice factor in the verification of the one-time password and the various levels of authentications for a full-security guarantee. The improvement provided by this proposal is mainly designed for sensitive applications. From conducted simulations, findings prove the efficiency of the proposed scheme in reducing the probability of hacking users' sessions.