Attentive Temporal Pooling for Conformer-Based Streaming Language Identification in Long-Form Speech
Quan Wang, Yu Yang, Jason Pelecanos, Yiling Huang, Ignacio López Moreno
Abstract
In this paper, we introduce a novel language identification system based on conformer layers.We propose an attentive temporal pooling mechanism to allow the model to carry information in long-form audio via a recurrent form, such that the inference can be performed in a streaming fashion.Additionally, we investigate two domain adaptation approaches to allow adapting an existing language identification model without retraining the model parameters for a new domain.We perform a comparative study of different model topologies under different constraints of model size, and find that conformer-based models significantly outperform LSTM and transformer based models.Our experiments also show that attentive temporal pooling and domain adaptation improve model accuracy.