Publications

Found 15 results
Author Title [ Type(Desc)] Year
Filters: Author is Suman Ravuri  [Clear All Filters]
Conference Paper
Shriberg, E., Stolcke A., & Ravuri S. (2013).  Addressee Detection for Dialog Systems Using Temporal and Spectral Dimensions of Speaking Style.
Valente, F., Magimai-Doss M., Plahl C., Ravuri S., & Wang W. (2010).  A Comparative Large Scale Study of MLP Features for Mandarin ASR. 2630-2633.
Meyer, B. T., Ravuri S., Schädler M. René, & Morgan N. (2011).  Comparing Different Flavors of Spectro-Temporal Features for ASR. 1269-1272.
Vinyals, O., & Ravuri S. (2011).  Comparing Multilayer Perceptron to Deep Belief Network Tandem Features for Robust ASR.
Ravuri, S., & Ellis D. P. W. (2010).  Cover Song Detection: From High Scores to General Classification. 65-68.
Ravuri, S., & Morgan N. (2012).  Easy Does It: Robust Spectro-Temporal Many-Stream ASR Without Fine Tuning Streams. 4309-4312.
Valente, F., Magimai-Doss M., Plahl C., & Ravuri S. (2009).  Hierarchical Processing of the Modulation Spectrum for GALE Mandarin LVCSR System. 2963-2966.
Ravuri, S., & Wegmann S. (2016).  How neural network depth compensates for HMM conditional independence assumptions in DNN-HMM acoustic models. Proceedings of Interspeech 2016.
Ravuri, S. (2014).  Hybrid MLP/Structured-SVM Tandem Systems for Large Vocabulary and Robust ASR.
Kingsbury, B., Soltau H.., Saon G.., Chu S.., Kuo H.-K.., Mangu L.., et al. (2011).  The IBM 2009 GALE Arabic Speech Transcription System. 4672-4675.
Zhao, S. Y., Ravuri S., & Morgan N. (2009).  Multi-Stream to Many-Stream: Using Spectro-Temporal Features for ASR. 2951-2954.
Ravuri, S., & Stolcke A. (2014).  Neural Network Models for Lexical Addressee Detection.
Ravuri, S., & Morgan N. (2010).  Using Spectro-Temporal Features to Improve AFE Feature Extraction for ASR. 1181-1184.