• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.04a
• /
• pp.288-289
• /
• 2012

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.10a
• /
• pp.703-704
• /
• 2012

• Journal of Software Assessment and Valuation
• /
• v.17 no.1
• /
• pp.101-113
• /
• 2021

In this paper, we introduce a speaker overlap system and look at the process of converting the existed system on the specific framework of artificial intelligence. Speaker overlap is when two or more speakers speak at the same time during a conversation, and can lead to performance degradation in the fields of speech recognition or speaker recognition, and a lot of research is being conducted because it can prevent performance degradation. Recently, as application of artificial intelligence is increasing, there is a demand for switching between artificial intelligence frameworks. However, when switching frameworks, performance degradation is observed due to the unique characteristics of each framework, making it difficult to switch frameworks. In this paper, the process of converting the speaker overlap detection system based on the Keras framework to the pytorch-based system is explained and considers components. As a result of the framework switching, the pytorch-based system showed better performance than the existing Keras-based speaker overlap detection system, so it can be said that it is valuable as a fundamental study on systematic framework conversion.

• Phonetics and Speech Sciences
• /
• v.4 no.4
• /
• pp.155-162
• /
• 2012

The population of Korea is ageing as the number of elderly people increases due to improvements in health care and diet. Accordingly, it is expected that interest in how to live actively during the years after retirement and how to communicate effectively will increase the demand for voice improvement methods and technology. However, the criteria to evaluate the voice strength and characteristics of the elderly are lacking. In this study, we analyzed the acoustic characteristics of elderly women living in the community according to residential status and mental health status (e.g. depressive mood). Accordingly, we selected women (n=63) above the age of 65 age who were living in the Seoul metropolitan area and Daegu Gyeongbuk. The selected subjects were divided into two groups: a normal speaker group (n=40) and a speaker group comprised of those suffering from depressive mood (n=23). This study analyzed the voice characteristics of subjects based on collected data through the sustained phonation of the vowel /a/. It was shown that there were differences among MPT, F0, Jitter, Shimmer and NHR depending on location of residence but no difference with regard to depressive mood. Therefore, we must consider location of residence in elderly as the key factor in demonstrating the voice norms of seniors.

• (The)Study of the Eastern Classic
• /
• no.41
• /
• pp.121-148
• /
• 2010

The aim of this paper is to look into the characteristics and its value of Jo Uin(曺友仁)'s Jadosa(自悼詞). I compared Jadosa with other Yeongungasa(戀君歌辭) works for this purposes in the sides of aspect of Yeongunuisik(戀君意識) and emotionalism. Therefore Jadosa is equipped with space setting called the heavenly world and the earthly world, and has characteristics that a speaker of the earthly world misses a lover of the heavenly world. Also, Jadosa is similar to Samiingok(思美人曲) and Sokmiingok(續美人曲) of Jeong Cheol(鄭澈) because the former borrowed a few phrases and motifs from the latter. However, if I look into Jadosa in greater detail in the sides of emotion or attitude of a speaker, the speaker of Jadosa shows a reproachful attitude Unlike works of Jeong Cheol. And the speaker of Jadosa urges the lover to be aware of his illusion. Finally these differences occur as a political standing and a relation with the king is different in every writer. Accordingly This paper is very worthwhile through comparison of Jadosa and other Yeongungasa works given that I reviewed characteristics and a meaning of Jadosa.

• Language and Information
• /
• v.17 no.2
• /
• pp.93-121
• /
• 2013

Identifying the speakers of individual utterances mentioned in textual stories is an important step towards developing applications that involve the use of unique characteristics of speakers in stories, such as robot storytelling and story-to-scene generation. Despite the usefulness, it is a challenging task because not only human entities but also animals and even inanimate objects can become speakers especially in fairytales so that the number of candidates is much more than that in other types of text. In addition, since the action of speaking is not always mentioned explicitly, it is necessary to infer the speaker from the implicitly mentioned speaking behaviors such as appearances or emotional expressions. In this paper, we investigate a method to exploit linguistic clues to identify the speakers of utterances from textual fairytale stories in Korean, especially in order to handle such challenging issues. Compared with the previous work, the present work takes into account additional linguistic features such as vocative roles and pairs of conversation participants, and proposes the use of discourse-level turn-taking behaviors between speakers to further reduce the number of possible candidate speakers. We describe a simple rule-based method to choose a speaker from candidates based on such linguistic features and turn-taking behaviors.

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.600-602
• /
• 1997

In this study, a hybrid neural net consisting of an Adaptive LVQ(ALVQ) algorithm and MLP is proposed to perform speaker identification task. ALVQ is a new learning procedure using adaptively feature vector sequence instead of only one feature vector in training codebooks initialized by LBG algorithm and the optimization criterion of this method is consistent with the speaker classification decision rule. ALVQ aims at providing a compressed, geometrically consistent data representation. It is fit to cover irregular data distributions and computes the distance of the input vector sequence from its nodes. On the other hand, MLP aim at a data representation to fit to discriminate patterns belonging to different classes. It has been shown that MLP nets can approximate Bayesian "optimal" classifiers with high precision, and their output values can be related a-posteriori class probabilities. The different characteristics of these neural models make it possible to devise hybrid neural net systems, consisting of classification modules based on these two different philosophies. The proposed method is compared with LBG algorithm, LVQ algorithm and MLP for performance.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.16 no.10 s.115
• /
• pp.997-1004
• /
• 2006

With the growth in electronics and the remarkable advance in wireless communication technology, mobile devices, such as mobile phones and PDAs are incessantly improved in their diverse functional performance. Lighter weight and smaller size has been gradually accomplished by recent circuit integration technology resulting in rapid growth in the number of mobile phone subscribers. Driven by customer demand, recent mobile devices are fully capable of realizing a variety of dazzling multimedia effects powered by electro-acoustic parts that have become one of the generic components. However, This paper also presents an oval micro-speaker, that is' expected to show an excellent performance within limited space of mobile phone, and its performance design has been suggested as well. Finally, a statistical approach to achieve high characteristic and performance is suggested by Taguchi method to identify a certain relationship between a mobile phone and a micro-speaker.

• International journal of advanced smart convergence
• /
• v.5 no.4
• /
• pp.21-25
• /
• 2016

Recent development in multi-channel surround is emerging in various formats to provide better stereoscopic and sound effects to consumers in recent broadcasting. The ability sound localize the sound sources in space is most considerable design factor on multi-channel surround system for human earing perception model. However, this paper propose the change of the sound localization according to the spacing of the speakers, which is not covered in the existing research focus on sound system design. Presently the sound system uses the position and number of the speakers to localize the sound. In the multi-channel surround environment, the proposed design uses the sound localization is caused by the directional characteristics of the speaker, the distance between the speakers and the distance between the listener and the speaker according to the directivity is required. The proposed design is simulated using virtual measurement with MATLAB simulation environment and performances are measured.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11a
• /
• pp.493-496
• /
• 2005

With the growth in electronics and the remarkable advance in wireless communication technology, mobile devices, such as mobile phones and PDAs are incessantly improved in their diverse functional performance. Lighter weight and smaller size has been gradually accomplished by recent circuit integration technology resulting in rapid growth in the number of mobile phone subscribers. Driven by customer demand, recent mobile devices are fully capable of realizing a variety of dazzling multimedia effects powered by electro-acoustic parts that have become one of the generic components. However, this paper also presents an oval micro-speaker, that is expected to show an excellent performance within limited space of mobile phone, and its performance design has been suggested as well. Finally, a statistical approach to achieve high characteristic and performance is suggested by Taguchi method to identify a certain relationship between a mobile phone and a micro-speaker.