Showing eess.ASShow all
2 papers · 1 filter
eess.AS2026
Progressive Alignment Objectives for Aligner-Encoder based ASR
Jaeyoung Lee, Masato Mimura, Takafumi Moriya
Aligner-Encoders are recently proposed seq2seq end-to-end ASR models that replace decoder attention by predicting the uth token directly from the u-th encoder position, so the enco…
eess.AS2026
Decoder-only Conformer with Modality-aware Sparse Mixtures of Experts for ASR
Jaeyoung Lee, Masato Mimura
We present a decoder-only Conformer for automatic speech recognition (ASR) that processes speech and text in a single stack without external speech encoders or pretrained large lan…