Merge Phd thesis refs/lohrenz

.gitignore

@@ -1,3 +1,4 @@
 *.bak
 *.sav
 .idea/
+*.log

ifn_spaml_bibliography.bib

@@ -1209,6 +1209,13 @@ @Book{Bishop2006
   publisher       = {Springer-Verlag}
 }
 
+@Book{Bishop2023,
+  title           = {{Deep Learning: Foundations and Concepts}},
+  author          = {Christopher M. Bishop and Hugh Bishop},
+  year            = {2023},
+  publisher       = {Springer-Verlag}
+}
+
 @InProceedings{Blau2017,
   title           = {{The Perception-Distortion Tradeoff}},
   author          = {Yochai Blau and Tomer Michaeli},
@@ -3005,6 +3012,17 @@ @InProceedings{Dabouei2020
   groups          = {Adversarial Example Training}
 }
 
+@Article{Dahl2012,
+  title           = {{Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition}}, 
+  author          = {George E. Dahl and Dong Yu and Li Deng and Alex Acero},
+  journal         = {IEEE Transactions on Audio, Speech, and Language Processing},
+  year            = {2012},
+  volume          = {20},
+  number          = {1},
+  pages           = {30--42},
+  month           = jan
+}
+
 @InProceedings{Dai2009,
   title           = {{Distortion-Rate Functions for Quantized Compressive Sensing}},
   author          = {W. {Dai} and H. V. {Pham} and O. {Milenkovic}},
@@ -5190,6 +5208,13 @@ @InProceedings{He2023b
   month           = may
 }
 
+@Book{Hebb1949,
+  title           = {{The Organization of Behavior - A Neuropsychological Theory}},
+  author          = {Donald Olding Hebb},
+  year            = {1949},
+  publisher       = {John Wiley \& Sons, Ltd.}
+}
+
 @Article{Hegde2007,
   title           = {{Significance of the Modified Group Delay Feature in Speech Recognition}},
   author          = {R. M. Hegde and H. A. Murthy and V. R. R. Gadde},
@@ -5710,6 +5735,14 @@ @InProceedings{Hu2022
   month           = apr
 }
 
+@Book{Huang2001,
+  title        = {{Spoken Language Processing: A Guide to Theory, Algorithm, and System Development}},
+  author       = {Xuedong Huang and Alex Acero and Hsiao-Wuen Hon},
+  year         = {2001},
+  publisher    = {Prentice Hall PTR},
+  address      = {Upper Saddle River, NJ}
+}
+
 @InProceedings{Huang2016,
   title           = {{Deep {Networks} With {Stochastic} {Depth}}},
   author          = {Huang, Gao and Sun, Yu and Liu, Zhuang and Sedra, Daniel and Weinberger, Kilian Q.},
@@ -6204,6 +6237,14 @@ @InProceedings{Jayaraman2015
   month           = jun
 }
 
+@Book{Jelinek1997,
+  title        = {{Statistical Methods for Speech Recognition}},
+  author       = {Jelinek, Frederick},
+  year         = {1997},
+  publisher    = {MIT Press},
+  address      = {Cambridge, MA}
+}
+
 @Article{Jeong2019,
   title           = {{Complex Urban Dataset with Multi-level Sensors from Highly Diverse Urban Environments}},
   author          = {Jeong, Jinyong and Younggun Cho, Young-Sik Shin and Hyunchul Roh and Ayoung Kim},
@@ -9149,6 +9190,17 @@ @Article{McCowan2005
   keywords        = {Signal Processing, Meetings}
 }
 
+@Article{McCulloch1943,
+  title           = {{A Logical Calculus of the Ideas Immanent in Nervous Activity}},
+  author          = {Warren S. McCulloch and Walter Pitts},
+  journal         = {The Bulletin of Mathematical Biophysics},
+  year            = {1943},
+  volume          = {5},
+  pages           = {115-–133},
+  month           = dec,
+  keywords        = {Neural Networks}
+}
+
 @InProceedings{McDermott2019,
   title           = {{A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition}},
   author          = {Erik McDermott and Hasim Sak and Ehsan Variani},
@@ -9338,6 +9390,16 @@ @Article{Michieli2019a
   note            = {(arXiv:1911.03462)}
 }
 
+@InProceedings{Mikolov2012,
+  title           = {{Context Dependent Recurrent Neural Network Language Model}},
+  author          = {Tomas Mikolov and Geoffrey Zweig},
+  booktitle       = {Proc. of SLT},
+  year            = {2012},
+  pages           = {234--239},
+  address         = {Miami, FL, USA},
+  month           = dec
+}
+
 @Article{Minaee2020image,
   title           = {{Image Segmentation Using Deep Learning: A Survey}},
   author          = {Minaee, Shervin and Boykov, Yuri and Porikli, Fatih and Plaza, Antonio and Kehtarnavaz, Nasser and Terzopoulos, Demetri},
@@ -15443,7 +15505,7 @@ @Book{Yu2015
 }
 
 @Book{Yu2015b,
-  title           = {Automatic Speech Recognition: A Deep Learning Approach},
+  title           = {{Automatic Speech Recognition: A Deep Learning Approach}},
   author          = {Dong Yu and Li Deng},
   year            = {2015},
   publisher       = {Springer-Verlag London},
@@ -15622,6 +15684,17 @@ @InProceedings{Zagoruyko2017
   comment         = {Align the student representation of some layers to be equal to the teacher representation of some layer. The authors term it attention transfer. Basically a feature matching approach.}
 }
 
+@InProceedings{Zeghidour2018,
+  title           = {{End-to-End Speech Recognition From the Raw Waveform}},
+  author    = {Neil Zeghidour and Nicolas Usunier and Gabriel Synnaeve and Ronan Collobert and Emmanuel Dupoux},
+  booktitle       = {{Proc.\ of Interspeech}},
+  year            = {2018},
+  pages           = {781--785},
+  address         = {Hyderabad, India},
+  month           = sep,
+  keywords        = {Emotion Recognition}
+} 
+
 @InProceedings{Zeiler2010deconvolutional,
   title           = {{Deconvolutional Networks}},
   author          = {Zeiler, Matthew D. and Krishnan, Dilip and Taylor, Graham W. and Fergus, Rob},