A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models
arXiv:2005.09336
Abstract
Following the rationale of end-to-end modeling, CTC, RNN-T or encoder-decoder-attention models for automatic speech recognition (ASR) use graphemes or grapheme-based subword units based on e.g. byte-pair encoding (BPE). The mapping from pronunciation to spelling is learned completely from data. In contrast to this, classical approaches to ASR employ secondary knowledge sources in the form of phoneme lists to define phonetic output labels and pronunciation lexica. In this work, we do a systematic comparison between grapheme- and phoneme-based output labels for an encoder-decoder-attention ASR model. We investigate the use of single phonemes as well as BPE-based phoneme groups as output labels of our model. To preserve a simplified and efficient decoder design, we also extend the phoneme set by auxiliary units to be able to distinguish homophones. Experiments performed on the Switchboard 300h and LibriSpeech benchmarks show that phoneme-based modeling is competitive to grapheme-based encoder-decoder-attention modeling.
arXiv comment5 pages, 6 tables
References in corpus (12)
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- Sequence Transduction with Recurrent Neural Networks
- A Comparative Study on Transformer vs RNN in Speech Applications
- Improved training of end-to-end attention models for speech recognition
- Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
- A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition
- RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition
- A New Training Pipeline for an Improved Neural Transducer
- Latent Sequence Decompositions
- An investigation of phone-based subword units for end-to-end speech recognition
- Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models