Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer
This work addresses computational inefficiency in speech separation systems for real-time applications, though it is incremental as it builds on existing Transformer-based methods.
The paper tackles the inefficiency and performance degradation of using deep Transformer models for multi-channel speech separation when overlap between speakers is low, by proposing an early exit mechanism that adapts model depth to input difficulty. Experimental results show that this approach accelerates inference and improves separation accuracy.
With its strong modeling capacity that comes from a multi-head and multi-layer structure, Transformer is a very powerful model for learning a sequential representation and has been successfully applied to speech separation recently. However, multi-channel speech separation sometimes does not necessarily need such a heavy structure for all time frames especially when the cross-talker challenge happens only occasionally. For example, in conversation scenarios, most regions contain only a single active speaker, where the separation task downgrades to a single speaker enhancement problem. It turns out that using a very deep network structure for dealing with signals with a low overlap ratio not only negatively affects the inference efficiency but also hurts the separation performance. To deal with this problem, we propose an early exit mechanism, which enables the Transformer model to handle different cases with adaptive depth. Experimental results indicate that not only does the early exit mechanism accelerate the inference, but it also improves the accuracy.