Abstract
Several types of Semi-Continuous HMM (SC-HMM) have been compared with the Continuous Density HMM (CD-HMM) in the context of Speaker Independent Isolated Words Recognition (SI-IWR). It is demonstrated that for the ten-digit vocabulary (TIDIGITS), the SC-HMM outperforms the CD-HMM when memory constraints are imposed on the system. SC-HMMs demonstrate recognition rate of about 95% with a total of 59 Gaussians, while under similar conditions the CD-HMM yield recognition rates of well below 80%. An algorithm for optimal selection of Gaussian functions for SC-HMM is presented.
| Original language | English |
|---|---|
| Pages | 1515-1518 |
| Number of pages | 4 |
| State | Published - 1 Jan 1999 |
| Externally published | Yes |
| Event | 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999 - Budapest, Hungary Duration: 5 Sep 1999 → 9 Sep 1999 |
Conference
| Conference | 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999 |
|---|---|
| Country/Territory | Hungary |
| City | Budapest |
| Period | 5/09/99 → 9/09/99 |
ASJC Scopus subject areas
- Computer Science Applications
- Software
- Linguistics and Language
- Communication