Small-footprint Deep Neural Networks with Highway Connections for Speech Recognition
This work addresses the challenge of deploying DNN-based acoustic models on resource-constrained platforms like mobile devices, representing an incremental improvement in efficiency.
The paper tackled the problem of large model parameters in deep neural networks for speech recognition by applying highway networks to train smaller, thinner, and deeper DNNs, achieving comparable accuracy with significantly reduced parameters on the AMI corpus.
For speech recognition, deep neural networks (DNNs) have significantly improved the recognition accuracy in most of benchmark datasets and application domains. However, compared to the conventional Gaussian mixture models, DNN-based acoustic models usually have much larger number of model parameters, making it challenging for their applications in resource constrained platforms, e.g., mobile devices. In this paper, we study the application of the recently proposed highway network to train small-footprint DNNs, which are {\it thinner} and {\it deeper}, and have significantly smaller number of model parameters compared to conventional DNNs. We investigated this approach on the AMI meeting speech transcription corpus which has around 70 hours of audio data. The highway neural networks constantly outperformed their plain DNN counterparts, and the number of model parameters can be reduced significantly without sacrificing the recognition accuracy.