An Investigation Of Phone-based Subword Units For End-to-end Speech Recognition

Abstract

Phones and their context-dependent variants have been the standard modeling units for conventional speech recognition systems, while characters and subwords have demonstrated their effectiveness for end-to-end recognition systems. We investigate the use of phone-based subwords, in particular, byte pair encoder (BPE), as modeling units for end-to-end speech recognition. In addition, we also developed multi-level language model-based decoding algorithms based on a pronunciation dictionary. Besides the use of the lexicon, which is easily available, our system avoids the need of additional expert knowledge or processing steps from conventional systems. Experimental results show that phone-based BPEs tend to yield more accurate recognition systems than the character-based counterpart. In addition, further improvement can be obtained with a novel one-pass joint beam search decoder, which efficiently combines phone- and character-based BPE systems. For Switchboard, our phone-based BPE system

Stats

• citations18
• S2 citations—
• github stars0
• HF likes0
• heat score9.59
• arxiv keywang2020an

Related papers

• Hybrid Ctc-attention Based End-to-end Speech Recognition Using Subword Units (2018)10.85
• A Systematic Comparison Of Grapheme-based Vs. Phoneme-based Label Units For Encoder-decoder-attention Models (2020)0.00
• Allost: Low-resource Speech Translation Without Source Transcription (2021)7.81
• Subword And Crossword Units For CTC Acoustic Models (2017)8.60
• Bytes Are All You Need: End-to-end Multilingual Speech Recognition And Synthesis With Bytes (2018)14.15
• The Effectiveness Of Unsupervised Subword Modeling With Autoregressive And Cross-lingual Phone-aware Networks (2020)2.26
• Subword Regularization: An Analysis Of Scalability And Generalization For End-to-end Automatic Speech Recognition (2020)5.24
• Word Segmentation On Discovered Phone Units With Dynamic Programming And Self-supervised Scoring (2022)9.23