Abstract Unlike traditional (hybrid) Automatic Speech Recognition (ASR), end-to-end ASR
systems simplify the training procedure by directly map** acoustic features to sequences …

Transfer learning from high-resource languages is known to be an efficient way to improve
end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or …

TV subtitles are a rich source of transcriptions of many types of speech, ranging from read
speech in news reports to conversational and spontaneous speech in talk shows and soaps …

Many semi-and weakly-supervised approaches have been investigated for overcoming the
labeling cost of building high quality speech recognition systems. On the challenging task of …

N-best list rescoring, an essential step in hybrid automatic speech recognition (ASR), aims to
re-evaluate the N-best hypothesis list decoded by the acoustic model (AM) and language …

End-to-end modeling requires tremendous amounts of transcribed speech to achieve an
automatic speech recognition (ASR) model with high performance. For low-resource ASR …