Name
Abstract | ||
|---|---|---|
This paper presents novel methods that integrate lexical prediction of non-verbalized punctuations with Viterbi decoding for Large Vocabulary Conversational Speech Recognition (LVCSR) in a single pass. We describe two different approaches - one based on a modified finite state machine representation of language models and one based on an extension of an LVCSR decoder. We discuss advantages over traditional punctuation prediction approaches based on post-processing of recognition hypotheses, including experimental evaluation of the proposed approach using a state-of-the-art LVCSR decoder. Experiments were performed on a medical documentation corpus and results demonstrate that the proposed methods yield improved punctuation prediction accuracy while at the same time reducing system complexity and memory requirements. |
Year | Venue | Keywords |
|---|---|---|
2008 | INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5 | Punctuation Prediction, Sentence Boundary Detection, Speech Recognition |
Field | DocType | Citations |
Single pass,Medical documents,Computer science,Artificial intelligence,Natural language processing,Language model,Pattern recognition,Speech recognition,Finite-state machine,Viterbi decoder,Decoding methods,Vocabulary,Punctuation | Conference | 0 |
PageRank | References | Authors |
0.34 | 4 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Anoop Deoras | 1 | 240 | 29.36 |
| Jürgen Fritsch | 2 | 22 | 4.75 |