Loading...
Please wait, while we are loading the content...
Similar Documents
Audio-visual large vocabulary continuous speech recognition in the broadcast domain (1999)
| Content Provider | CiteSeerX |
|---|---|
| Author | Rajput, N. Neti, C. Subramaniam, L. Basu, S. Verma, A. |
| Abstract | Abstract- We consider the problem of combining visual cues with audio signals for the purpose of improved automatic machine recognition of speech. Although signi cant progress has been made in machine transcription of large vocabulary continuous speech (LVCSR) over the last few years, the technology to date is most e ective only under controlled conditions such aslow noise, speaker dependent recognition and read speech (as opposed to conversational speech) etc. On the otherhand, while augmenting the recognition of speech utterances with visual cues has attracted the attention of researchers over the last couple of years, most e orts in this domain can be considered to be only preliminary in the sense that unlike LVCSR e orts, tasks have been limited to small vocabulary (e.g., command, digits) and often to speaker dependent training or isolated word speech where word boundaries are arti cially well de ned. |
| File Format | |
| Publisher Date | 1999-01-01 |
| Access Restriction | Open |
| Subject Keyword | Lvcsr Orts Signi Cant Progress Condition Aslow Noise Broadcast Domain Large Vocabulary Continuous Speech Speech Utterance Dependent Training Word Boundary Improved Automatic Machine Recognition Speaker Dependent Recognition Word Speech Machine Transcription |
| Content Type | Text |
| Resource Type | Article |
