• 한국인터넷방송통신학회논문지
• /
• 제11권4호
• /
• pp.181-186
• /
• 2011

본 논문에서는 잡음 환경에서의 음성인식 개선에 관한 내용으로 기존의 DTW에서 일종의 특징보상기법을 적용한 방식으로 예측잡음이 아닌 실생활에서의 음성잡음 데이터를 적용하여 인식모델을 잡음상황에 맞도록 적응시키는 방법으로 제안하는 Noise Cancel DTW를 사용하였다. 음성인식 시 주변노이즈를 고려한 참조패턴을 생성하여 특징 보상으로 인식률을 향상 시키는 방법으로 잡음 환경에서 음성 인식률을 향상 시켰다.

• 한국정보통신학회논문지
• /
• 제15권4호
• /
• pp.817-822
• /
• 2011

본 논문에서는 먼저 신경회로망의 학습에 오차역전파 학습 알고리즘을 사용하여 각 프레임에서의 음성 및 잡음 구간의 검출에 의한 음성인식 알고리즘을 제안한다. 그리고 신경회로망에 의하여 음성 및 잡음 구간의 검출에 따라서 각 프레임에서 잡음을 제거하는 스펙트럼 차감법을 제안한다. 본 실험에서는 제안한 음성인식알고리즘의 성능을 원음성에 백색잡음 및 자동차 잡음을 부가하여 인식율을 평가한다. 또한 인식시스템에 의하여 검출된 음성 및 잡음 구간을 이용하여 각 프레임에서의 스펙트럼 차감법에 의한 잡음제거의 실험결과를 나타낸다. 잡음에 의하여 오염된 음성에 대하여 신호대잡음비를 사용하여 본 알고리즘이 유효하다는 것을 확인한다.

• ETRI Journal
• /
• 제46권1호
• /
• pp.22-34
• /
• 2024

Exposure to varied noisy environments impairs the recognition performance of artificial intelligence-based speech recognition technologies. Degraded-performance services can be utilized as limited systems that assure good performance in certain environments, but impair the general quality of speech recognition services. This study introduces an audiovisual speech recognition (AVSR) model robust to various noise settings, mimicking human dialogue recognition elements. The model converts word embeddings and log-Mel spectrograms into feature vectors for audio recognition. A dense spatial-temporal convolutional neural network model extracts features from log-Mel spectrograms, transformed for visual-based recognition. This approach exhibits improved aural and visual recognition capabilities. We assess the signal-to-noise ratio in nine synthesized noise environments, with the proposed model exhibiting lower average error rates. The error rate for the AVSR model using a three-feature multi-fusion method is 1.711%, compared to the general 3.939% rate. This model is applicable in noise-affected environments owing to its enhanced stability and recognition rate.

• 음성과학
• /
• 제6권
• /
• pp.219-233
• /
• 1999

This paper presents a real-time implementation of a speaker independent speech recognition system based on a discrete hidden markov model(DHMM). This system is developed for a car navigation system to design on-chip VLSI system of speech recognition which is used by fixed point Oak DSP core of DSP GROUP LTD. We analyze recognition procedure with C language to implement fixed point real-time algorithms. Based on the analyses, we improve the algorithms which are possible to operate in real-time, and can verify the recognition result at the same time as speech ends, by processing all recognition routines within a frame. A car noise is the colored noise concentrated heavily on the low frequency segment under 400 Hz. For the noise robust processing, the high pass filtering and the liftering on the distance measure of feature vectors are applied to the recognition system. Recognition experiments on the twelve isolated command words were performed. The recognition rates of the baseline recognizer were 98.68% in a stopping situation and 80.7% in a running situation. Using the noise processing methods, the recognition rates were enhanced to 89.04% in a running situation.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2004년도 춘계 학술대회 발표논문집
• /
• pp.231-234
• /
• 2004

This paper describes an efficient method for improving the noise-robustness in speech recognition in a running car by considering wind noise. In driving car, mainly three kind of noises engine noise, tire noise and wind noise, are severely affect recognition performance. Especially wind noise is an important factor in driving car with window opened. We analyzed wind noise in various driving conditions that are 60, 80, 100 km/h with window fully opened, window half opened. We clarified that the recognition rate is significantly degenerated when the wind noise components in the frequency range above 200 Hz are large. We developed a preprocessing method to improve the noise robustness despite of wind noise. We adaptively changed the cutoff frequency of the front-end high-pass filter from 100 through 200 Hz according to the level of the wind noise components. By this method, the recognition rate is considerably improved for all kind of driving conditions

• 전자공학회논문지 IE
• /
• 제49권2호
• /
• pp.9-17
• /
• 2012

음성 인식 시스템의 용용에서 실제 문제점의 하나는 음성신호의 왜곡에 의한 인식성능의 저하이다. 음성신호의 왜곡에 가장 중요한 원인은 부가적인 잡음이다. 이 논문은 잡음에 강인한 음성인식을 위하여, 스펙트럼 피크 향상 기법과 효과적인 잡음 차감 기법에 기초한 스펙트럼 보상 방법을 기술한다. 제안한 방법은 음성 스펙트럼의 포먼트 구조를 향상시키고 스펙트럼 기울기를 보상하면서도 광 대역폭 스펙트럼 요소는 그대로 유지한다. 백색 가우스 잡음, 자동차 잡음, 음성 잡음 또는 지하철 잡음에 의해 왜곡된 음성을 이용한 인식실험을 수행한 결과, 새로운 방법은 스펙트럼 보상을 하지 않은 경우에 비해, 높은 SNR(Signal to Noise Ratio) 환경에서는 평균 오인식율을 약간 줄였으며, 낮은 SNR(10 dB) 환경에서는 평균 오인식율을 1/2로 크게 줄였다.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 FIFTH WESTERN PACIFIC REGIONAL ACOUSTICS CONFERENCE SEOUL KOREA
• /
• pp.1015-1020
• /
• 1994

This paper presents the Korean digit recognition method under noise environment using the spectral mapping training based on static supervised adaptation algorithm. In the presented recognition method, as a result of spectral mapping from one space of noisy speech spectrum to another space of speech spectrum without noise, spectral distortion of noisy speech is improved, and the recognition rate is higher than that of the conventional method using VQ and DTW without noise processing, and even when SNR level is 0 dB, the recognition rate is 10 times of that using the conventional method. It has been confirmed that the spectral mapping training has an ability to improve the recognition performance for speech in noise environment.

• 한국정밀공학회지
• /
• 제23권5호
• /
• pp.68-76
• /
• 2006

The ability to recognize human emotion is one of the hallmarks of human-robot interaction. Hence this paper describes the realization of emotion recognition. For emotion recognition from voice, we propose a new feature called frequency range of meaningful signal. With this feature, we reached average recognition rate of 76% in speaker-dependent. From the experimental results, we confirm the usefulness of the proposed feature. We also define the noise environment and conduct the noise-environment test. In contrast to other features, the proposed feature is robust in a noise-environment.

• 디지털융복합연구
• /
• 제13권8호
• /
• pp.295-300
• /
• 2015

사전 확률분포를 모델링하는 HMM을 사용하는 어휘 인식에서 인식 어휘의 모델들의 대한 인식 확률이 이산적인 분포를 나타내며 인식을 위한 계산량이 적은 장점이 있지만 인식률을 계산했을 때 상대적으로 낮은 단점이 있다. 이를 개선하기 위하여 베이시안 기법 어휘 인식 모델을 융합한 잡음 제거 인식률 향상을 제안한다. 본 논문은 베이시안 기법 어휘 인식을 위한 모델 구성을 베이시안 기법의 최적화한 인식 모델을 구성하였다. HMM을 기반으로 한 사전 확률 방법과 베이시안 기법인 사후확률을 융합하여 잡음을 제거하고 인식률을 향상시켰다. 본 논문에서 제안한 방법을 적용한 결과 어휘 인식률에서 98.1%의 인식률을 나타내었다.

• 대한치과기공학회지
• /
• 제36권2호
• /
• pp.111-118
• /
• 2014

Purpose: Production of dental prosthesis by a dental technician causes a loud noise. Thus, we investigated stress of dental technicians due to a noise using a structured questionnaire. Methods: A survey was conducted on working dental technicians across the country from July 2013 to November 2013; among 200 sets of survey distributed, 166 were completed and returned, and excluding the 11 that deemed unsuitable, 155 sets were used for statistics. The program SPSS 19.0 was used to analyze the correlation among the collected data. Results: The stress of noise was found to be 2.83/5 points (2.93/5 for physical stress, 2.72/5 for emotional stress). Recognition of noise was found to be 2.71/5 points (3.39/5 for recognition of noise, 2.64/5 for accidents caused by noise, 2.29/5 for experiencing disability due to noise). For general items, the highest stress were shown for the following catogories: by gender, females (p=.008); by position, chief engineer (p=.033); by monthly pay, 2.51M-3.0M KRW (p=.023); by interior comfort, 'very unpleasant' was the highest recognized (p=.014). For the effect of time exposed to noise, its stress (p=.000) and recognition (p=.000) rose with increase of time. Conclusion: Dental technicians performs tasks in work environments exposed to extreme noise. This research attempts to re-emphasize the necessity for improving the work environment for noise and provide measures of blocking noise and precaution.