Work place: School of Computing, Telkom University, Bandung, West Java 40257, Indonesia



Research Interests: Computer systems and computational processes, Artificial Intelligence, Computational Learning Theory, Swarm Intelligence


Suyanto was born in Jombang, East Java, Indonesia, in 1974. He received the B.Sc. on Informatics Engineering from Sekolah Tinggi Teknologi Telkom or STT Telkom (now Telkom University), Bandung, Indonesia in 1998, the M.Sc. on Complex Adaptive Systems from Chalmers University of Technology in 2006 and Ph.D. on Computer Science from Universitas Gadjah Mada in 2016. Since 2000, he joined STT Telkom (now Telkom University), School of Computing, as a lecturer. His research interests include speech processing, computational linguistics, artificial intelligence, machine learning, deep learning, and swarm intelligence.

Author Articles
Optimizing Parameters of Automatic Speech Segmentation into Syllable Units

By Riksa Meidy Karim Suyanto

DOI:, Pub. Date: 8 May 2019

An automatic speech segmentation into syllable is an important task in a modern syllable-based speech recognition. It is generally developed using a time-domain energy-based feature and a static threshold to detect a syllable boundary. The main problem is the fixed threshold should be defined exhaustively to get a high generalized accuracy. In this paper, an optimization method is proposed to adaptively find the best threshold. It optimizes the parameters of syllable speech segmentation and exploits two post-processing methods: iterative-splitting and iterative-assimilation. The optimization is carried out using three independent genetic algorithms (GAs) for three processes: boundary detection, iterative-splitting, and iterative-assimilation. Testing to an Indonesian speech dataset of 110 utterances shows that the proposed iterative-splitting with optimum parameters reduce deletion errors more than the commonly used non-iterative-splitting. The optimized iterative-assimilation is capable of removing more insertions, without over-merging, than the common non-iterative-assimilation. The sequential combination of optimized iterative-splitting and optimized iterative-assimilation gives the highest accuracy with the lowest deletion and insertion errors.

[...] Read more.
Other Articles