原创力文档- 6
- 0
- 约2.45万字
- 约 8页
- 2018-01-02 发布于天津
- 举报
论文
Enhancing Spontaneous Speech Recognition
with BLSTM Features
Martin W¨ollmer and Bj¨orn Schuller
Institute for Human-Machine Communication,
Technische Universit¨at M¨unchen, 80333 M¨unchen, Germany
woellmer@tum.de
Abstract. This paper introduces a novel context-sensitive feature ex-
traction approach for spontaneous speech recognition. As bidirectional
Long Short-Term Memory (BLSTM) networks ar
您可能关注的文档
- 论文-6071-generative-shape-models-joint-text-recognition-and-segmentation-with-very-little-training-data.pdf
- 论文-An overview of gradient descent optimizationalgorithms.pdf
- 论文-Attention with Intention for a Neural Network Conversation Model.pdf
- 论文-Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models.pdf
- 论文-cimpoi15deep.pdf
- 论文-Deconvolution.pdf
- 论文-Deep Residual Learning for Image Recognition.pdf
- 论文-Feedforward Sequential Memory Networks- A New Structure to Learn Long-term Dependency.pdf
- 论文-How NOT To Evaluate Your Dialogue System- An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation.pdf
- 论文-Is Faster R-CNN Doing Well for Pedestrian Detection.pdf
- 论文-On-Manifold Preintegration for Real-Time vio.pdf
- 论文-Positive matrix factorization_ A non-negative factor model with optimal utilization of error estimates of data values †.pdf
- 论文-The Ubuntu Dialogue Corpus- A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems.pdf
- 论文-Vector Representations of Words.pdf
- 论文-What_Makes_for_Effective_Detection_Proposals.pdf
- 论文-YOLO9000.pdf
文档评论（0）