Loading...
Please wait, while we are loading the content...
Similar Documents
EFFICIENT SEARCH ALGORITHMS FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION (1996)
| Content Provider | CiteSeerX |
|---|---|
| Author | Deshmukh, Neeraj |
| Abstract | Automatic speaker-independent speech recognition has made significant progress from the days of isolated word recognition. Today state of the art systems are capable of performing large-vocabulary continuous speech recognition (LVCSR) over complex domains such as news broadcasts and telephone conversations. A significant contribution to this advancement in technology is due to the development of search techniques that support efficient, sub-optimal decoding over large search spaces and complex statistical models. Moreover, these decoding strategies are capable of dynamically integrating information from a number of diverse knowledge sources to determine the correct word hypothesis. In this |
| File Format | |
| Publisher Date | 1996-01-01 |
| Access Restriction | Open |
| Subject Keyword | Art System News Broadcast Significant Progress Today State Telephone Conversation Complex Domain Isolated Word Recognition Complex Statistical Model Large-vocabulary Continuous Speech Recognition Sub-optimal Decoding Large Search Space Automatic Speaker-independent Speech Recognition Diverse Knowledge Source Significant Contribution Search Technique Correct Word Hypothesis |
| Content Type | Text |
