Word embeddings for speech recognition

Citations Over TimeTop 10% of 2014 papers

Abstract

Speech recognition systems have used the concept of states as a way to decompose words into sub-word units for decades. As the number of such states now reaches the number of words used to train acoustic models, it is interesting to consider approaches that relax the assumption that words are made of states. We present here an alternative construction, where words are projected into a continuous embedding space where words that sound alike are nearby in the Euclidean sense. We show how embeddings can still allow to score words that were not in the training dictionary. Initial experiments using a lattice rescoring approach and model combination on a large realistic dataset show improvements in word error rate.

Related Papers

• → How to Generate a Good Word Embedding(2016)316 cited
• → A speaker-stress resistant HMM isolated word recognizer(2005)53 cited
• → Improving speech recognition by explicit modeling of phone deletions(2010)4 cited
• MFCC와 LPC 특징 추출 방법을 이용한 음성 인식 오류 보정(2013)
• → Dual embedding with input embedding and output embedding for better word representation(2022)