Speaker-Utterance Dual Attention for Speaker and Utterance Verification
This work addresses verification accuracy in speech processing, offering a domain-specific improvement for tasks like speaker and utterance verification.
The paper tackles the problem of improving speaker and utterance verification by exploiting the interaction between speaker traits and linguistic content, achieving superior performance over competitive systems on the RSR2015 corpus.
In this paper, we study a novel technique that exploits the interaction between speaker traits and linguistic content to improve both speaker verification and utterance verification performance. We implement an idea of speaker-utterance dual attention (SUDA) in a unified neural network. The dual attention refers to an attention mechanism for the two tasks of speaker and utterance verification. The proposed SUDA features an attention mask mechanism to learn the interaction between the speaker and utterance information streams. This helps to focus only on the required information for respective task by masking the irrelevant counterparts. The studies conducted on RSR2015 corpus confirm that the proposed SUDA outperforms the framework without attention mask as well as several competitive systems for both speaker and utterance verification.