Title | ||
---|---|---|
Incorporating speech recognition confidence into discriminative named entity recognition of speech data |
Abstract | ||
---|---|---|
This paper proposes a named entity recognition (NER) method for speech recognition results that uses confidence on automatic speech recognition (ASR) as a feature. The ASR confidence feature indicates whether each word has been correctly recognized. The NER model is trained using ASR results with named entity (NE) labels as well as the corresponding transcriptions with NE labels. In experiments using support vector machines (SVMs) and speech data from Japanese newspaper articles, the proposed method outperformed a simple application of text-based NER to ASR results in NER F-measure by improving precision. These results show that the proposed method is effective in NER for noisy inputs. |
Year | DOI | Venue |
---|---|---|
2006 | 10.3115/1220175.1220253 | ACL |
Keywords | Field | DocType |
automatic speech recognition,incorporating speech recognition confidence,asr confidence feature,text-based ner,speech recognition result,speech data,entity recognition,ner f-measure,asr result,ner model,speech recognition,support vector machine | Transcription (linguistics),Computer science,Support vector machine,Named entity,Speech recognition,Artificial intelligence,Natural language processing,Discriminative model,Named-entity recognition | Conference |
Volume | Citations | PageRank |
P06-1 | 12 | 0.77 |
References | Authors | |
16 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Katsuhito Sudoh | 1 | 326 | 34.44 |
Hajime Tsukada | 2 | 449 | 29.46 |
Hideki Isozaki | 3 | 934 | 64.50 |