Lexical-phonetic automata for spoken utterance indexing and retrieval


Fayolle J., SARAÇLAR M., Moreau F., Raymond C., Gravier G.

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, Portland, OR, Amerika Birleşik Devletleri, 9 - 13 Eylül 2012, cilt.3, ss.2469-2472, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 3
  • Basıldığı Şehir: Portland, OR
  • Basıldığı Ülke: Amerika Birleşik Devletleri
  • Sayfa Sayıları: ss.2469-2472
  • Anahtar Kelimeler: Confidence measures, Edit distances, Information retrieval, Lexical-phonetic automata, Speech indexing, Supervised learning
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

This paper1 presents a method for indexing spoken utterances which combines lexical and phonetic hypotheses in a hybrid index built from automata. The retrieval is realised by a lexical-phonetic and semi-imperfect matching whose aim is to improve the recall. A feature vector, containing edit distance scores and a confidence measure, weights each transition to help the filtering of the candidate utterance list for a more precise search. Experiment results show that the lexical and phonetic representations are complementary and we compare the hybrid search with the state-of-the-art cascaded search to retrieve named entity queries.