Self-Learning Speaker Identification [electronic resource] :A System for Enhanced Speech Recognition / by Tobias Herbig, Franz Gerl, Wolfgang Minker.
by Herbig, Tobias [author.]; Gerl, Franz [author.]; Minker, Wolfgang [author.]; SpringerLink (Online service).
Material type:
BookSeries: Signals and Communication Technology: Publisher: Berlin, Heidelberg : Springer Berlin Heidelberg, 2011.Description: XII, 172 p. online resource.ISBN: 9783642198991.Subject(s): Engineering | Computer science | Biometrics | Telecommunication | Engineering | Signal, Image and Speech Processing | Biometrics | Communications Engineering, Networks | User Interfaces and Human Computer InteractionDDC classification: 621.382 Online resources: Click here to access online | Item type | Current location | Call number | Status | Date due | Barcode |
|---|---|---|---|---|---|
| TA1637-1638 (Browse shelf) | Available | ||||
| TK7882.S65 (Browse shelf) | Available | ||||
| Long Loan | MAIN LIBRARY | TK5102.9 (Browse shelf) | Available |
Close shelf browser
| TJ210.2-211.495 Agents and Artificial Intelligence | Q334-342 Privacy and Security Issues in Data Mining and Machine Learning | TJ210.2-211.495 Privacy and Security Issues in Data Mining and Machine Learning | TA1637-1638 Self-Learning Speaker Identification | GB1001-1199.8 Advances in the Research of Aquatic Environment | RS400-431 Ion Channels and Their Inhibitors | R895-920 Advances in Radiation Oncology in Lung Cancer |
Introduction -- State of the Art -- Fundamentals -- Speech Production -- Front-End -- Speaker Change -- Speaker Identification.-Speaker Adaptation.
Current speech recognition systems suffer from variation of voice characteristics between speakers as they are usually based on speaker independent speech models. In order to resolve this issue, adaptation methods have been developed in many state-of-the-art systems. However, information acquired over time is still lost whenever another speaker intermittently uses the recognition system. This work therefore develops an integrated approach for speech and speaker recognition in order to improve the self-learning opportunities of the system. A speaker adaptation scheme is introduced. It is suited for fast short-term and detailed long-term adaptation. These adaptation profiles are then used for an efficient speaker recognition system. The speaker identification enables the speaker adaptation to track different speakers which results in an optimal long-term adaptation.
There are no comments for this item.