A Unified Deep Neural Network for Speaker and Language Recognition
This work addresses the need for efficient multi-task learning in speech processing, offering significant performance gains for speaker and language recognition applications.
The paper tackled the problem of speaker and language recognition by proposing a unified deep neural network that handles both tasks simultaneously, achieving a 55% reduction in equal error rate (EER) for out-of-domain speaker recognition and a 48% reduction in EER for 30-second language recognition.
Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains are possible using a single DNN for both speaker and language recognition. The unified DNN approach is shown to yield substantial performance improvements on the the 2013 Domain Adaptation Challenge speaker recognition task (55% reduction in EER for the out-of-domain condition) and on the NIST 2011 Language Recognition Evaluation (48% reduction in EER for the 30s test condition).