Subword And Crossword Units For CTC Acoustic Models

Abstract

This paper proposes a novel approach to create an unit set for CTC based speech recognition systems. By using Byte Pair Encoding we learn an unit set of an arbitrary size on a given training text. In contrast to using characters or words as units this allows us to find a good trade-off between the size of our unit set and the available training data. We evaluate both Crossword units, that may span multiple word, and Subword units. By combining this approach with decoding methods using a separate language model we are able to achieve state of the art results for grapheme based CTC systems.

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keyzenkel2017subword

Related papers

• Hybrid Ctc-attention Based End-to-end Speech Recognition Using Subword Units (2018)10.85
• An Investigation Of Phone-based Subword Units For End-to-end Speech Recognition (2020)9.59
• Advancing CTC-CRF Based End-to-end Speech Recognition With Wordpieces And Conformers (2021)0.00
• Hierarchical Conditional End-to-end ASR With CTC And Multi-granular Subword Units (2021)9.23
• Multilingual Training And Cross-lingual Adaptation On Ctc-based Acoustic Model (2017)0.00
• Comparison Of Decoding Strategies For CTC Acoustic Models (2017)10.48
• A Systematic Comparison Of Grapheme-based Vs. Phoneme-based Label Units For Encoder-decoder-attention Models (2020)0.00
• Neural Speech Recognizer: Acoustic-to-word LSTM Model For Large Vocabulary Speech Recognition (2016)15.16