The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results
This addresses the problem of scarce data and lack of benchmarks for code-switching speech recognition, primarily benefiting researchers in speech technology, though it is incremental as it builds on existing ASR frameworks.
The paper tackled the challenge of Mandarin-English code-switching speech recognition by releasing datasets and organizing a competition, resulting in improved ASR performance through methods like pronunciation lexicon and data augmentation in traditional systems, and language identification and spec-augment in end-to-end models.
Code-switching (CS) is a common phenomenon and recognizing CS speech is challenging. But CS speech data is scarce and there' s no common testbed in relevant research. This paper describes the design and main outcomes of the ASRU 2019 Mandarin-English code-switching speech recognition challenge, which aims to improve the ASR performance in Mandarin-English code-switching situation. 500 hours Mandarin speech data and 240 hours Mandarin-English intra-sentencial CS data are released to the participants. Three tracks were set for advancing the AM and LM part in traditional DNN-HMM ASR system, as well as exploring the E2E models' performance. The paper then presents an overview of the results and system performance in the three tracks. It turns out that traditional ASR system benefits from pronunciation lexicon, CS text generating and data augmentation. In E2E track, however, the results highlight the importance of using language identification, building-up a rational set of modeling units and spec-augment. The other details in model training and method comparsion are discussed.