Albert Zeyer

Investigations on Phoneme-Based End-To-End Speech Recognition.

2020 · arXiv (Cornell University)

Common end-to-end models like CTC or encoder-decoder-attention models use characters or subword units like BPE as the output labels. We do systematic comparisons between grapheme-based and phoneme-based output labels. These can be single phonemes without …

Improved Training of End-to-end Attention Models for Speech Recognition

2018

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h tasks. In particular, we …