Phone-aware Neural Language Identification
This work addresses language identification for speech processing, offering a domain-specific improvement by integrating phonetic knowledge into neural systems.
The authors tackled the problem of language identification (LID) by incorporating phonetic information into neural models, which had been largely overlooked, and achieved significant performance improvements, as demonstrated in experiments on four languages from the Babel corpus.
Pure acoustic neural models, particularly the LSTM-RNN model, have shown great potential in language identification (LID). However, the phonetic information has been largely overlooked by most of existing neural LID models, although this information has been used in the conventional phonetic LID systems with a great success. We present a phone-aware neural LID architecture, which is a deep LSTM-RNN LID system but accepts output from an RNN-based ASR system. By utilizing the phonetic knowledge, the LID performance can be significantly improved. Interestingly, even if the test language is not involved in the ASR training, the phonetic knowledge still presents a large contribution. Our experiments conducted on four languages within the Babel corpus demonstrated that the phone-aware approach is highly effective.