We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
Convolutional neural networks (CNNs) are a standard component of many current state-of-the-art Large Vocabulary Continuous Speech Recognition (LVCSR) systems. However, CNNs in LVCSR have not kept pace with recent advances in other domains where deeper neural networks provide superior performance. In this paper we propose a number of architectural advances in CNNs for LVCSR. First, we introduce a very deep convolutional network architecture with up to 14 weight layers. There are multiple convolutional layers before each pooling layer, with small 3x3 kernels, inspired by the VGG Imagenet 2014 architecture. Then, we introduce multilingual CNNs with multiple untied layers. Finally, we introduce multi-scale input features aimed at exploiting more context at negligible computational cost. We evaluate the improvements first on a Babel task for low resource speech recognition, obtaining an absolute 5.77% WER improvement over the baseline PLP DNN by training our CNN on the combined data of six different languages. We then evaluate the very deep CNNs on the Hub5'00 benchmark (using the 262 hours of SWB-1 training data) achieving a word error rate of 11.8% after cross-entropy training, a 1.4% WER improvement (10.6% relative) over the best published CNN result so far.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1509.08967")
get_code_for_paper("1509.08967")
have("1509.08967")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1509.08967.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1509.08967)
Connect an agent — have() is free.