Entropy-based false detection filtering in spoken term detection tasks

Natori, Satoshi; Furuya, Yuto; Nishizaki, Hiromitsu; Sekiguchi, Y.

doi:10.1109/apsipa.2013.6694352

Cited by 3 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although our DTW-based approach using a PTNformed index for STD was very robust against ASR errors, the approach outputted many false detections from a PTN with a complex structure [7]. It is difficult to speechrecognize correctly an utterance including OOV words or unclearly pronounced words.…”

Section: Introductionmentioning

confidence: 99%

Re-Ranking Approach of Spoken Term Detection Using Conditional Random Fields-Based Triphone Detection

Sawada

Nishizaki

2016

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARY This study proposes a two-pass spoken term detection (STD) method. The first pass uses a phoneme-based dynamic time warping (DTW)-based STD, and the second pass recomputes detection scores produced by the first pass using conditional random fields (CRF)-based triphone detectors. In the second-pass, we treat STD as a sequence labeling problem. We use CRF-based triphone detection models based on features generated from multiple types of phoneme-based transcriptions. The models train recognition error patterns such as phoneme-to-phoneme confusions in the CRF framework. Consequently, the models can detect a triphone comprising a query term with a detection probability. In the experimental evaluation of two types of test collections, the CRF-based approach worked well in the re-ranking process for the DTW-based detections. CRF-based re-ranking showed 2.1% and 2.0% absolute improvements in F-measure for each of the two test collections.

show abstract

Section: Introductionmentioning

confidence: 99%