Sorry, you need to enable JavaScript to visit this website.

Word Characters and Phone Pronunciation Embedding for ASR Confidence Classifier

Citation Author(s):
Kshitiz Kumar, Tasos Anastasakos, Yifan Gong
Submitted by:
Kshitiz Kumar
Last updated:
7 May 2019 - 3:33pm
Document Type:
Document Year:
Kshitiz Kumar
Paper Code:

Confidences are integral to ASR systems, and applied to data selection, adaptation, ranking hypotheses, arbitration etc.Hybrid ASR system is inherently a match between pronunciations and AM+LM evidence but current confidence features lack pronunciation information. We develop pronunciation embeddings to represent and factorize acoustic score in relevant bases, and demonstrate 8-10% relative reduction in false alarm (FA) on large scale tasks. We generalize to standard NLP embeddings like Glove, and show 16% relative reduction in FA in combination with Glove.

0 users have voted: