• 대한임베디드공학회논문지
• /
• 제3권1호
• /
• pp.1-7
• /
• 2008

In this paper, a MSS-NOVO method that combines the HMM composition method with a noise reduction method is proposed for speech recognition in noisy environments. This combined method starts with noise reduction with modified spectral subtraction (MSS) to enhance the input noisy speech, then the noise and voice composition (NOVO) method is applied for making noise adapted models by using the noise in the non-utterance regions of the enhanced noisy speech. In order to evaluate the effectiveness of our proposed method, we compare MSS-NOVO method with other methods, i.e., SS-NOVO, MWF-NOVO. To set up the noisy speech for test, we add White noise to KLE 452 database with different SNRs range from 0dB to 15dB, at 5dB intervals. From the tests, MSS-NOVO method shows average improvement of 66.5% and 13.6% compared with the existing SS-NOVO method and MWF-NOVO method, respectively. Especially our proposed MSS-NOVO method shows a big improvement at low SNRs.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• 제25권3호
• /
• pp.194-210
• /
• 2022

Human milk contains a number of nutritional and bioactive molecules including microorganisms that constitute the so-called "Human Milk Microbiota (HMM)". Recent studies have shown that not only bacterial but also viral, fungal, and archaeal components are present in the HMM. Previous research has established, a "core" microbiome, consisting of Firmicutes (i.e., Streptococcus, Staphylococcus), Proteobacteria (i.e., Serratia, Pseudomonas, Ralstonia, Sphingomonas, Bradyrhizobium), and Actinobacteria (i.e., Propionibacterium, Corynebacterium). This review aims to summarize the main characteristics of HMM and the role it plays in shaping a child's health. We reviewed the most recent literature on the topic (2019-2021), using the PubMed database. The main sources of HMM origin were identified as the retrograde flow and the entero-mammary pathway. Several factors can influence its composition, such as maternal body mass index and diet, use of antibiotics, time and type of delivery, and mode of breastfeeding. The COVID-19 pandemic, by altering the mother-infant dyad and modifying many of our previous habits, has emerged as a new risk factor for the modification of HMM. HMM is an important contributor to gastrointestinal colonization in children and therefore, it is fundamental to avoid any form of perturbation in the HMM that can alter the microbial equilibrium, especially in the first 100 days of life. Microbial dysbiosis can be a trigger point for the development of necrotizing enterocolitis, especially in preterm infants, and for onset of chronic diseases, such as asthma and obesity, later in life.

• 한국음향학회지
• /
• 제25권4호
• /
• pp.159-163
• /
• 2006

본 논문에서는 잡음음성인식을 위한 데이터 기반의 향상된 Jacobian 적응 방식을 제안하였다. Jacobian 적응에서 필요로 하는 기준 HMM을 구성하기 위해서 기존에 주로 사용되던 모델결합 방식을 사용하는 대신에 잡음음성을 이용하여 직접 훈련하는 방식을 제안하였다. 이렇게 함으로서 기존의 방법에 비해서 잡음에 의한 음향모델의 변이를 보다 잘 처리할 수 있을 것으로 생각된다 제안된 방법에서는 Jacobian 행렬의 추정을 위해서 훈련과정에서 Baum-Welch 알고리듬을 사용하였다. 잡음음성에 대한 인식실험을 통해서 제안된 방식이 기존의 Jacobian 적응 방식 뿐 만 아니라 다른 형태의 모델적응 방식들에 비해서도 우수한 성능을 보임을 알 수 있었다.