• 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.

• Proceedings of the KSPS conference
• /
• 2004.05a
• /
• pp.125-130
• /
• 2004

In this paper, we explain telecommunication services based on spoken language information technology. There are three different kinds of services. The first is based on Advanced Intelligent services(AIN). We built a Intelligent Peripheral(IP)with speech recognition, speech synthesis and VoiceXML interpreter. The second is based on KT-HUVOIS, a proprietary speech platform based on VoiceXML. The third is based on VoiceXML interpreter. We explain various services depending on these platforms in detail.

• KIISE Transactions on Computing Practices
• /
• v.21 no.8
• /
• pp.531-536
• /
• 2015

The speech recognition is an active research area in the human computer interface (HCI). The objective of this study is to control digital devices with voices. In addition, the mouse is used as a computer peripheral tool which is widely used and provided in graphical user interface (GUI) computing environments. In this paper, we propose a method of controlling the mouse with the real-time speech recognition function of a smartphone. The processing steps include extracting the core voice signal after receiving a proper length voice input with real time, to perform the quantization by using the learned code book after feature extracting with mel frequency cepstral coefficient (MFCC), and to finally recognize the corresponding vowel using hidden markov model (HMM). In addition a virtual mouse is operated by mapping each vowel to the mouse command. Finally, we show the various mouse operations on the desktop PC display with the implemented smartphone application.

• ETRI Journal
• /
• v.45 no.4
• /
• pp.678-689
• /
• 2023

This paper describes a novel end-to-end deep generative model-based speaker recognition system using prosodic features. The usefulness of variational autoencoders (VAE) in learning the speaker-specific prosody representations for the speaker recognition task is examined herein for the first time. The speech signal is first automatically segmented into syllable-like units using vowel onset points (VOP) and energy valleys. Prosodic features, such as the dynamics of duration, energy, and fundamental frequency (F₀), are then extracted at the syllable level and used to train/adapt a speaker-dependent VAE from a universal VAE. The initial comparative studies on VAEs and traditional autoencoders (AE) suggest that the former can efficiently learn speaker representations. Investigations on the impact of gender information in speaker recognition also point out that gender-dependent impostor banks lead to higher accuracies. Finally, the evaluation on the NIST SRE 2010 dataset demonstrates the usefulness of the proposed approach for speaker recognition.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.4
• /
• pp.201-207
• /
• 2013

Voice Recognition technique has been developed and it has been actively applied to various information devices such as smart phones and car navigation system. But the basic research technique related the speech recognition is based on research results in English. Since the lip sync producing generally requires tedious hand work of animators and it serious affects the animation producing cost and development period to get a high quality lip animation. In this research, a real time processed automatic lip sync algorithm for virtual characters in digital contents is studied by considering Korean vocal sound system. This suggested algorithm contributes to produce a natural lip animation with the lower producing cost and the shorter development period.

• MALSORI
• /
• no.50
• /
• pp.51-69
• /
• 2004

In this paper, we present a one-pass semi-dynamic network decoding framework that inherits both advantages of fast decoding speed from static network decoders and memory efficiency from dynamic network decoders. Our method is based on the novel language model network representation that is essentially of finite state machine (FSM). The static network derived from the language model network [1][2] is partitioned into smaller subnetworks which are static by nature or self-structured. The whole network is dynamically managed so that those subnetworks required for decoding are cached in memory. The network is near-minimized by applying the tail-sharing algorithm. Our decoder is evaluated on the 25k-word Korean broadcast news transcription task. In case of the search network itself, the network is reduced by 73.4% from the tail-sharing algorithm. Compared with the equivalent static network decoder, the semi-dynamic network decoder has increased at most 6% in decoding time while it can be flexibly adapted to the various memory configurations, giving the minimal usage of 37.6% of the complete network size.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• pp.1027-1032
• /
• 1994

This paper introduces a interword modeling and a Viterbi search method for continuous speech recognition. We also describe a development of a real-time voice dialing system which can recognize around one hundred words and continuous digits in speaker independent mode. For continuous digit recognition, between-word units have been proposed to provide a more precise representation of word junctures. The best path in HMM is found by the Viterbi search algorithm, from which digit sequences are recognized. The simulation results show that a interword modeling using the context-dependent between-word units provide better recognition rates than a pause modeling using the context-independent pause unit. The voice dialing system is implemented on a DSP board with a telephone interface plugged in an IBM PC AT/486.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.178-185
• /
• 2021

Sequence to sequence(S2S) 기반 음성인식 후처리기를 훈련하기 위한 학습 데이터 구축을 위해 (음성인식 결과(speech recognition sentence), 전사자(phonetic transcriptor)가 수정한 문장(Human post edit sentence))의 병렬 말뭉치가 필요하며 이를 위해 많은 노동력(human-labor)이 소요된다. BackTranScription (BTS)이란 기존 S2S기반 음성인식 후처리기의 한계점을 완화하기 위해 제안된 데이터 구축 방법론이며 Text-To-Speech(TTS)와 Speech-To-Text(STT) 기술을 결합하여 pseudo 병렬 말뭉치를 생성하는 기술을 의미한다. 해당 방법론은 전사자의 역할을 없애고 방대한 양의 학습 데이터를 자동으로 생성할 수 있기에 데이터 구축에 있어서 시간과 비용을 단축 할 수 있다. 본 논문은 BTS를 바탕으로 제주어 도메인에 특화된 음성인식 후처리기의 성능을 향상시키기 위하여 모델 수정(model modification)을 통해 성능을 향상시키는 모델 중심 접근(model-centric) 방법론과 모델 수정 없이 데이터의 양과 질을 고려하여 성능을 향상시키는 데이터 중심 접근(data-centric) 방법론에 대한 비교 분석을 진행하였다. 실험결과 모델 교정없이 데이터 중심 접근 방법론을 적용하는 것이 성능 향상에 더 도움이 됨을 알 수 있었으며 모델 중심 접근 방법론의 부정적 측면 (negative result)에 대해서 분석을 진행하였다.

• Journal of Computing Science and Engineering
• /
• v.2 no.1
• /
• pp.1-25
• /
• 2008

Spoken dialog tasks incur many errors including speech recognition errors, understanding errors, and even dialog management errors. These errors create a big gap between the user's intention and the system's understanding, which eventually results in a misinterpretation. To fill in the gap, people in human-to-human dialogs try to clarify the major causes of the misunderstanding to selectively correct them. This paper presents a method of clarification techniques to human-to-machine spoken dialog systems. We viewed the clarification dialog as a two-step problem-Belief confirmation and Clarification strategy establishment. To confirm the belief, we organized the clarification process into three systematic phases. In the belief confirmation phase, we consider the overall dialog system's processes including speech recognition, language understanding and semantic slot and value pairs for clarification dialog management. A clarification expert is developed for establishing clarification dialog strategy. In addition, we proposed a new design of plugging clarification dialog module in a given expert based dialog system. The experiment results demonstrate that the error verifiers effectively catch the word and utterance-level semantic errors and the clarification experts actually increase the dialog success rate and the dialog efficiency.

• Journal of the Korean Society of Industry Convergence
• /
• v.21 no.1
• /
• pp.17-27
• /
• 2018

We propose a new approach to control a biped robot motion based on iterative learning of voice command for the implementation of smart factory. The real-time processing of speech signal is very important for high-speed and precise automatic voice recognition technology. Recently, voice recognition is being used for intelligent robot control, artificial life, wireless communication and IoT application. In order to extract valuable information from the speech signal, make decisions on the process, and obtain results, the data needs to be manipulated and analyzed. Basic method used for extracting the features of the voice signal is to find the Mel frequency cepstral coefficients. Mel-frequency cepstral coefficients are the coefficients that collectively represent the short-term power spectrum of a sound, based on a linear cosine transform of a log power spectrum on a nonlinear mel scale of frequency. The reliability of voice command to control of the biped robot's motion is illustrated by computer simulation and experiment for biped walking robot with 24 joint.