Leveraging Language ID to Calculate Intermediate CTC Loss for Enhanced Code-Switching Speech Recognition
This work addresses the challenge of code-switching in speech recognition, which is a domain-specific issue for multilingual applications, and appears incremental as it builds on existing methods by integrating language ID into the model architecture.
The paper tackles the problem of performance degradation in end-to-end speech recognition models due to code-switching by introducing language identification into the encoder's middle layer to generate language-distinct acoustic features, aiming to reduce model confusion without specifying concrete numerical results.
In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional Automatic Speech Recognition model. It is possible to achieve human-like recognition without the need to build a pronunciation dictionary in advance. However, due to the relative scarcity of training data on code-switching, the performance of ASR models tends to degrade drastically when encountering this phenomenon. Most past studies have simplified the learning complexity of the model by splitting the code-switching task into multiple tasks dealing with a single language and then learning the domain-specific knowledge of each language separately. Therefore, in this paper, we attempt to introduce language identification information into the middle layer of the ASR model's encoder. We aim to generate acoustic features that imply language distinctions in a more implicit way, reducing the model's confusion when dealing with language switching.