In this paper, we present our initial efforts for building a code-switching (CS) speech recognition system leveraging existing acoustic models (AMs) and language models (LMs), i.e., no training required, and specifically targeting intra-sentential switching. To achieve such an ambitious goal, new mechanisms for foreign pronunciation generation and language model (LM) enrichment have been devised. Specifically, we have designed an automatic approach to obtain high quality pronunciation of foreign language (FL) words in the native language (NL) phoneme set using existing acoustic phone decoders and an LSTM-based grapheme-to-phoneme (G2P) model. Improved accented pronunciations have thus been obtained by learning foreign pronunciations directly from data. Furthermore, a code-switching LM was deployed by converting the original NL LM into a CS LM using translated word pairs and borrowing statistics for the NL LM. Experimental evidence clearly demonstrates that our approach better deals with accented foreign pronunciations than techniques based on human labeling. Moreover, our best system achieves a 55.5% relative word error rate reduction from 34.4%, obtained with a conventional monolingual ASR system, to 15.3% on an intra-sentential CS task without harming the monolingual recognition accuracy.
Huang, Z., Zhuang, X., Liu, D., Xiao, X., Zhang, Y., Siniscalchi, S.M. (2019). Exploring Retraining-free Speech Recognition for Intra-sentential Code-switching. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 6066-6070). IEEE [10.1109/ICASSP.2019.8682478].
Exploring Retraining-free Speech Recognition for Intra-sentential Code-switching
Siniscalchi, Sabato Marco
2019-01-01
Abstract
In this paper, we present our initial efforts for building a code-switching (CS) speech recognition system leveraging existing acoustic models (AMs) and language models (LMs), i.e., no training required, and specifically targeting intra-sentential switching. To achieve such an ambitious goal, new mechanisms for foreign pronunciation generation and language model (LM) enrichment have been devised. Specifically, we have designed an automatic approach to obtain high quality pronunciation of foreign language (FL) words in the native language (NL) phoneme set using existing acoustic phone decoders and an LSTM-based grapheme-to-phoneme (G2P) model. Improved accented pronunciations have thus been obtained by learning foreign pronunciations directly from data. Furthermore, a code-switching LM was deployed by converting the original NL LM into a CS LM using translated word pairs and borrowing statistics for the NL LM. Experimental evidence clearly demonstrates that our approach better deals with accented foreign pronunciations than techniques based on human labeling. Moreover, our best system achieves a 55.5% relative word error rate reduction from 34.4%, obtained with a conventional monolingual ASR system, to 15.3% on an intra-sentential CS task without harming the monolingual recognition accuracy.File | Dimensione | Formato | |
---|---|---|---|
0006066.pdf
Solo gestori archvio
Tipologia:
Versione Editoriale
Dimensione
198.65 kB
Formato
Adobe PDF
|
198.65 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
2109.00921v1.pdf
accesso aperto
Tipologia:
Post-print
Dimensione
201.42 kB
Formato
Adobe PDF
|
201.42 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.