Hasil Pencarian  ::  Simpan CSV :: Kembali

"This updated book expands upon prosody for recognition applications of speech processing. It includes importance of prosody for speech processing applications; builds on why prosody needs to be incorporated in speech processing applications; and presents methods for extraction and representation of prosody for applications such as speaker recognition, language recognition and speech recognition. The updated book also includes information on the significance of prosody for emotion recognition and various prosody-based approaches for automatic emotion recognition from speech."

"This book presents a statistical parametric speech synthesis (SPSS) framework for developing a speech synthesis system where the desired speech is generated from the parameters of vocal tract and excitation source. Throughout the book, the authors discuss novel source modeling techniques to enhance the naturalness and overall intelligibility of the SPSS system. This book provides several important methods and models for generating the excitation source parameters for enhancing the overall quality of synthesized speech. The contents of the book are useful for both researchers and system developers. For researchers, the book is useful for knowing the current state-of-the-art excitation source models for SPSS and further refining the source models to incorporate the realistic semantics present in the text. For system developers, the book is useful to integrate the sophisticated excitation source models mentioned to the latest models of mobile/smart phones.- Presents the efficient excitation source modeling techniques for generating high quality speech;- Includes a combination of both waveform and parametric methods to enhance the quality of synthesis;- Features and methods that need less memory and computational requirements than others, allowing them to be integrated to smart phones and smaller devices."

"ABSTRAKFitur suara dapat menjadi alternatif model interaksi pada perangkat tertanam yang dirancang tanpa memiliki banyak tombol kendali, seperti sistem bantu penderita buta warna yang dirancang, yang disebut Chromophore. Skripsi ini membandingkan kinerja fitur suara yang dibuat dengan SAPI5.1 dan fitur suara yang dibuat manual dengan metode penggabungan fonem dan DTW, untuk diimplementasikan pada Chromophore. Skripsi ini juga membandingkan kompatibilitas OS tertanam WinCE6 dan WES09 untuk mendukung fitur suara tersebut. Pengujian fitur suara dilakukan dengan 10 responden untuk mengenali kata-kata yang disintesis sistem dan mengucapkan kata agar dikenali sistem. Pengujian OS dilakukan dengan melihat ukuran, durasi boot, dan dukungannya terhadap aplikasi berfitur suara. Dari uji coba tersebut, diketahui bahwa fitur suara yang dibuat dengan SAPI5.1 memiliki kinerja yang lebih baik dibandingkan dengan fitur suara yang dibuat manual, dengan keberhasilan sintesis suara sebesar 88,33% dan pengenalan suara sebesar 75,87% pada kondisi tenang dan 74,76% pada kondisi bising. Pengujian kedua membuktikan WES09 lebih cocok digunakan dikarenakan dukungannya pada .NET 3.5 dan SAPI5.1.

---

ABSTRACTSpeech feature can be an alternative interaction model for embedded device, which is designed without many buttons for its control, such as color-blind aid system that is designed, namely Chromophore. This paper compares performance of a speech feature created using SAPI5.1 and a speech feature created manually using phone-concatenate and DTW, to be implemented in Chromophore. This paper also compares the compatibility of embedded operating systems, WinCE6 and WES09, to support the speech feature. The testing for speech feature is done using 10 respondents to identify words synthesized by the systems and to say words to be recognized by the systems. The testing for operating systems is done by observing their size, boot time, and their support for the speech feature. As the result, speech feature created using SAPI5.1 is better than the manually-created one, with success rate 88,33% for speech synthesis, 75,87% and 74,76% for speech recognition in silent and noisy condition. The second testing shows that WES09 is more suitable because of its support for .NET 3.5 and SAPI5.1. "