Hasil Pencarian  ::  Simpan CSV :: Kembali

"ABSTRACTDigital signal processing is concerned with the representation of signals by sequences of number or symbols and the processing of the sequences. The purpose of such processing may be to estimate characteristic parameters of a signal or to transform a signal into a form which is in some sense more desirable. The classical numerical analysis formulas, such as those designed for interpolation, integration, and differentiation, are certainly digital signal processing algorithms. The early work on speech and the like - topics still of considerable interest and still the object of active research began less than two decade ago. The rapid development of the subject can be appreciated by scanning the issues of the leading journals. Yet the application of digital signal processing has not been without its problems. It is a field which demands sophisticated technology. "

"Smart house systems require some information of human locations in the system environment, different smart house system offers different human tracking method. The idea of this paper is to determine which method is better in which condition."

"Informasi yang terdapat saat ini tidak hanya terbatas disimpan dalam bentuk dokumen teks saja, tetapi banyak juga dalam bentuk dokumen suara. Banyaknya informasi yang disimpan dalam bentuk dokumen suara menyebabkan diperlukannya teknik perolehan informasi yang dapat diterapkan kepada koleksi dokumen tersebut. Pendekatan yang banyak dilakukan adalah dengan menggunakan hasil pengenalan suara oleh Sistem Pengenalan Suara Otomatis (SPSO). Tetapi, hasil pengenalan suara oleh SPSO tidak sepenuhnya benar sehingga menurunkan tingkat akurasi perolehan informasi dokumen suara. Pada penelitian ini penulis mencoba empat jenis hasil pengenalan suara untuk melakukan perolehan informasi dokumen suara, yaitu 1-best output, n-best word output, n-best pronounciation output, word posterior lattice. Selain itu, penulis juga mencoba tiga jenis kueri pada penelitian ini, yaitu kueri satu kata, kueri frase dua kata dan kueri kalimat. Hasil yang didapat pada penelitian ini menyimpulkan bahwa penggunaan 1-best output pada perolehan informasi dokumen suara menghasilkan kinerja yang lebih baik dibandingkan penggunaan hasil pengenalan suara yang lain. Mean Average Precision (MAP) hasil eksperimen dengan 1-best output lebih besar 0.64% dibandingkan penggunaan n-best output , 8,88% lebih besar dibandingkan penggunaan word posterior lattice dan lebih besar 92.68% dibandingkan penggunaan n-best pronounciation output. Pada eksperimen dengan kueri frase, sistem dengan akurasi terbaik adalah sistem yang menggunakan word posterior lattice. Pada eksperimen dengan kueri satu kata dan kueri kalimat, sistem yang menggunakan n-best word output menghasilkan kinerja terbaik.

---

The information today is not only limited in the form of text documents, but also in the form of spoken documents. The growing number of those spoken documents requires the information retrieval techniques to make the retrieval process easier. The approach for spoken documents retrieval is using automatic speech recognition (ASR). However, the results of the speech recognition by ASR are not entirely correct, so reduce the level of accuracy of information retrieval of spoken documents. This experiment uses four types results of the speech recognition by ASR, the 1-best output, n-best output, n-best pronunciation output, word posterior lattice. In addition, this experiment also investigates the effect of the use of query types (phrase, single word and sentence). Results obtained from this experiment concluded that the use of 1-best output on spoken document retrieval produces better performance results than the use of other results of the speech recognition. Mean Average Precision (MAP) results of experiments with 1-best output is 0.64% higher than the use of n-best output, 8.88% higher than the use of word posterior lattice and 92.68% higher than the use of n-best pronunciation output. In phrase based query experiment, the best accuracy is word posterior lattice while the best accuracy in single word query and sentence query is n-best word output."

"This book is about recent research in the area of profiling humans from their voice, which seeks to deduce and describe the speaker's entire persona and their surroundings from voice alone. It covers several key aspects of this technology, describing how the human voice is unique in its ability to both capture and influence the human persona -- how, in some ways, voice is more potent and valuable then DNA and fingerprints as a metric, since it not only carries information about the speaker, but also about their current state and their surroundings at the time of speaking. It provides a comprehensive review of advances made in multiple scientific fields that now contribute to its foundations. It describes how artificial intelligence enables mechanisms of discovery that were not possible before in this context, driving the field forward in unprecedented ways. It also touches upon related and relevant challenges posed by voice disguise and other mechanisms of voice manipulation. The book acts as a good resource for academic researchers, and for professional agencies in many areas such as law enforcement, healthcare, social services, entertainment etc."