We propose an integrated framework for large vocabulary continuous mixed language
speech recognition that handles the accent effect in the bilingual acoustic model and the …

Traditional hybrid DNN-HMM based ASR system for keywords spotting which models HMM
states are not flexible to optimize for a specific language. In this paper, we construct an end …

This paper proposes using cross-lingual language modeling with syntactic information for
low-resource speech recognition. We propose phrase-level transduction and syntactic …

The use of weighted finite-state transducers (WFSTs) has become an attractive technique for
building large vocabulary continuous speech recognition decoders. Conventionally, the …

The article describes the main advantages of voice control systems, notes the shortcomings
of the first implemented voice control systems, their functional limitations, and limited use in …

This paper examines two strategies that improve the beam pruning behavior of DNN
acoustic models with only a negligible increase in model complexity. By augmenting the …

This paper proposes a first-ever phrase-level transduction model with reordering to
transform colloquial speech directly to written-style transcription. This model is capable of …

This paper proposes cross-lingual language modeling for transcribing source resourcepoor
languages and translating them into target resource-rich languages if necessary. Our focus …

情報処理技術, および音声認識技術の発展により, 大規模なデータを利用した音声認識が実現可能
となってきた. 今日の音声認識技術は, 機械学習に基づいており, 学習データが大規模であればある …