Collaborative Learning for Language and Speaker Recognition
This work addresses the need for efficient multi-modal recognition systems in speech processing, though it appears incremental as it combines existing tasks in a collaborative framework.
The paper tackled the problem of performing language and speaker recognition simultaneously by proposing a unified multi-task recurrent neural network model, which outperformed task-specific models on both tasks.
This paper presents a unified model to perform language and speaker recognition simultaneously and altogether. The model is based on a multi-task recurrent neural network where the output of one task is fed as the input of the other, leading to a collaborative learning framework that can improve both language and speaker recognition by borrowing information from each other. Our experiments demonstrated that the multi-task model outperforms the task-specific models on both tasks.