A Comparison Of Modeling Units In Sequence-to-sequence Speech Recognition With The Transformer On Mandarin Chinese

Abstract

The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units. However, it has been challenged by sequence-to-sequence attention-based models, which integrate an acoustic, pronunciation and language model into a single neural network. On English ASR tasks, previous attempts have already shown that the modeling unit of graphemes can outperform that of phonemes by sequence-to-sequence attention-based model. In this paper, we are concerned with modeling units on Mandarin Chinese ASR tasks using sequence-to-sequence attention-based models with the Transformer. Five modeling units are explored including context-independent phonemes (CI-phonemes), syllables, words, sub-words and characters. Experiments on HKUST datasets demonstrate that the lexicon free modeling units can outperform lexicon related modeling units in terms

Stats

• citations32
• S2 citations—
• github stars0
• HF likes0
• heat score11.39
• arxiv keyzhou2018a

Related papers

• Research On Modeling Units Of Transformer Transducer For Mandarin Speech Recognition (2020)0.00
• On The Choice Of Modeling Unit For Sequence-to-sequence Speech Recognition (2019)9.59
• A Systematic Comparison Of Grapheme-based Vs. Phoneme-based Label Units For Encoder-decoder-attention Models (2020)0.00
• Cascade Rnn-transducer: Syllable Based Streaming On-device Mandarin Speech Recognition With A Syllable-to-character Converter (2020)9.92
• Pronunciation-aware Unique Character Encoding For RNN Transducer-based Mandarin Speech Recognition (2022)3.58
• A Comparative Study On Transformer Vs RNN In Speech Applications (2019)20.07
• Multilingual End-to-end Speech Recognition With A Single Transformer On Low-resource Languages (2018)0.00
• Memory Augmented Lookup Dictionary Based Language Modeling For Automatic Speech Recognition (2022)0.00