Sorry, you need to enable JavaScript to visit this website.

Phoneme based Neural Transducer for Large Vocabulary Speech Recognition

Primary tabs

Citation Author(s):
Wei Zhou, Simon Berger, Ralf Schlüter, Hermann Ney
Submitted by:
Wei Zhou
Last updated:
22 June 2021 - 6:10am
Document Type:
Poster
Document Year:
2021
Event:
Presenters Name:
Wei Zhou
Paper Code:
SPE-1.5

Abstract 

Abstract: 

To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling. Different alignment label topologies are compared and word-end-based phoneme label augmentation is proposed to improve performance. Utilizing the local dependency of phonemes, we adopt a simplified neural network structure and a straightforward integration with the external word-level language model to preserve the consistency of seq-to-seq modeling. We also present a simple, stable and efficient training procedure using frame-wise cross-entropy loss. A phonetic context size of one is shown to be sufficient for the best performance. A simplified scheduled sampling approach is applied for further improvement and different decoding approaches are briefly compared. The overall performance of our best model is comparable to state-of-the-art (SOTA) results for the TED-LIUM Release 2 and Switchboard corpora.

up
0 users have voted:

Dataset Files

poster_Zhou_phoneme-transducer.pdf

(19)