LiteG2P: A fast, light and high accuracy model for grapheme-to-phoneme conversion
This addresses the need for fast, lightweight G2P models for on-device inference in ASR and TTS applications, representing an incremental improvement over existing methods.
The paper tackles the problem of grapheme-to-phoneme conversion by proposing LiteG2P, a model that integrates expert knowledge and CTC-based neural networks, achieving high accuracy with 10 times fewer parameters than a CTC-based method and comparable performance to a Transformer-based model with 33 times less computation.
As a key component of automated speech recognition (ASR) and the front-end in text-to-speech (TTS), grapheme-to-phoneme (G2P) plays the role of converting letters to their corresponding pronunciations. Existing methods are either slow or poor in performance, and are limited in application scenarios, particularly in the process of on-device inference. In this paper, we integrate the advantages of both expert knowledge and connectionist temporal classification (CTC) based neural network and propose a novel method named LiteG2P which is fast, light and theoretically parallel. With the carefully leading design, LiteG2P can be applied both on cloud and on device. Experimental results on the CMU dataset show that the performance of the proposed method is superior to the state-of-the-art CTC based method with 10 times fewer parameters, and even comparable to the state-of-the-art Transformer-based sequence-to-sequence model with less parameters and 33 times less computation.