End-to-end open vocabulary keyword search


Creative Commons License

Yusuf B., Gok A., Gundogdu B., SARAÇLAR M.

22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021, Brno, Çek Cumhuriyeti, 30 Ağustos - 03 Eylül 2021, cilt.2, ss.836-840, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 2
  • Doi Numarası: 10.21437/interspeech.2021-1399
  • Basıldığı Şehir: Brno
  • Basıldığı Ülke: Çek Cumhuriyeti
  • Sayfa Sayıları: ss.836-840
  • Anahtar Kelimeler: Keyword search, Spoken term detection
  • Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

Recently, neural approaches to spoken content retrieval have become popular. However, they tend to be restricted in their vocabulary or in their ability to deal with imbalanced test settings. These restrictions limit their applicability in keyword search, where the set of queries is not known beforehand, and where the system should return not just whether an utterance contains a query but the exact location of any such occurrences. In this work, we propose a model directly optimized for keyword search. The model takes a query and an utterance as input and returns a sequence of probabilities for each frame of the utterance of the query having occurred in that frame. Experiments show that the proposed model not only outperforms similar end-to-end models on a task where the ratio of positive and negative trials is artificially balanced, but it is also able to deal with the far more challenging task of keyword search with its inherent imbalance. Furthermore, using our system to rescore the outputs an LVCSR-based keyword search system leads to significant improvements on the latter.