Multi-Staged Cross-Lingual Acoustic Model Adaption for Robust Speech Recognition in Real-World Applications -- A Case Study on German Oral History Interviews
This work addresses the challenge of robust speech recognition for real-world applications like German oral history interviews, where data scarcity and domain mismatch are critical issues, representing an incremental improvement over existing adaptation methods.
The paper tackles the problem of poor speech recognition performance in domains with insufficient training data by proposing a multi-staged cross-lingual acoustic model adaptation approach, achieving a relative word error rate reduction of over 30% compared to a model trained only on target domain data and 6-7% compared to using same-language out-of-domain data.
While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks in domains that greatly deviate from the conditions represented by the training data. For many real-world applications, there is a lack of sufficient data that can be directly used for training robust speech recognition systems. To address this issue, we propose and investigate an approach that performs a robust acoustic model adaption to a target domain in a cross-lingual, multi-staged manner. Our approach enables the exploitation of large-scale training data from other domains in both the same and other languages. We evaluate our approach using the challenging task of German oral history interviews, where we achieve a relative reduction of the word error rate by more than 30% compared to a model trained from scratch only on the target domain, and 6-7% relative compared to a model trained robustly on 1000 hours of same-language out-of-domain training data.