You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
\item Dissertation Topic: Low latency modeling of temporal contexts for speech recognition
68
67
\item Advisor: Daniel Povey and Sanjeev Khudanpur
69
68
\end{list2}
70
69
\end{list1}
@@ -76,7 +75,7 @@ \section{\sc Education}
76
75
77
76
\begin{list2}
78
77
\vspace*{.05in}
79
-
\item Dissertation Topic: Synthesis of missing units in a Telugu text-to-speech system
78
+
\item Dissertation Topic: Synthesis of missing units in a Telugu text-to-speech system
80
79
\item Advisor: Kishore Prahallad
81
80
\end{list2}
82
81
\end{list1}
@@ -88,7 +87,7 @@ \section{\sc Education}
88
87
89
88
\begin{list2}
90
89
\vspace*{.05in}
91
-
\item Topic: Note Histogram based hash function for Content Based Music Information Retrieval (CBMIR)
90
+
\item Topic: Note Histogram based hash function for Content Based Music Information Retrieval (CBMIR)
92
91
\item Advisor: Vijaykumar Chakka
93
92
\end{list2}
94
93
\end{list1}
@@ -104,17 +103,26 @@ \section{\sc Achievements}
104
103
\section{\sc Publications}
105
104
\begin{enumerate}
106
105
107
-
\item\textbf{Vijayaditya Peddinti}, Guoguo Chen, Vimal Manohar, Tom Ko, Daniel Povey and Sanjeev Khudanpur,
108
-
\textit{JHU ASpIRE system: Robust LVCSR with TDNNs, iVector adaptation and RNN-LMs}, in Proceedings of ASRU 2015\\
106
+
\item\textbf{Vijayaditya Peddinti}, Yiming Wang, Daniel Povey and Sanjeev Khudanpur,
107
+
\textit{Low latency modeling of temporal contexts}, IEEE Signal Processing Letters, 2017\\
109
108
110
-
\item\textbf{Vijayaditya Peddinti}, Daniel Povey, Sanjeev Khudanpur,
111
-
\textit{A time delay neural network architecture for efficient modeling of long temporal contexts}, in Proceedings of INTERSPEECH 2015\\
112
-
\textbf{Best paper award}
109
+
\item\textbf{Vijayaditya Peddinti}, Vimal Manohar, Yiming Wang, Daniel Povey and Sanjeev Khudanpur,
110
+
\textit{Far-field ASR without parallel data}, in Proceedings of Interspeech 2016\\
113
111
114
112
\item\textbf{Vijayaditya Peddinti}, Guoguo Chen, Daniel Povey, Sanjeev Khudanpur,
115
113
\textit{Reverberation robust acoustic modeling using i-vectors with time delay neural networks}, in Proceedings of INTERSPEECH 2015\\
116
114
\textbf{Winner of the IARPA ASpIRE far field recognition challenge}
117
115
116
+
\item\textbf{Vijayaditya Peddinti}, Daniel Povey, Sanjeev Khudanpur,
117
+
\textit{A time delay neural network architecture for efficient modeling of long temporal contexts}, in Proceedings of INTERSPEECH 2015\\
118
+
\textbf{Best paper award}
119
+
120
+
\item\textbf{Vijayaditya Peddinti}, Guoguo Chen, Vimal Manohar, Tom Ko, Daniel Povey and Sanjeev Khudanpur,
121
+
\textit{JHU ASpIRE system: Robust LVCSR with TDNNs, iVector adaptation and RNN-LMs}, in Proceedings of ASRU 2015\\
122
+
123
+
\item Tara Sainath, \textbf{Vijayaditya Peddinti}, O. Siohan and A. Narayanan,
124
+
\textit{Annealed F-smoothing as a mechanism to speed up neural network training}, in Proceedings of INTERSPEECH 2017
125
+
118
126
\item Tom Ko, \textbf{Vijayaditya Peddinti}, Daniel Povey, Sanjeev Khudanpur,
119
127
\textit{Audio Augmentation for Speech Recognition}, in Proceedings of INTERSPEECH 2015
120
128
@@ -136,21 +144,15 @@ \section{\sc Publications}
136
144
\item Hynek Hermansky, Ehsan Variani and \textbf{Vijayaditya Peddinti},
137
145
\textit{Mean temporal distance: Predicting ASR error from temporal properties of speech signal}, in Proceedings of ICASSP 2013, Vancouver
138
146
139
-
\item Aren Jansen,et al,
147
+
\item Aren Jansen,et al,
140
148
\textit{A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition}, in Proceedings of ICASSP 2013, Vancouver
141
149
142
-
143
150
\item\textbf{Vijayaditya Peddinti} and Kishore Prahallad,
144
151
\textit{Significance of epenthesis for Text-To-Speech synthesis in Telugu}, in Proceedings of ICASSP, 2011, Prague
145
152
146
153
\item\textbf{Vijayaditya Peddinti} and Kishore Prahallad,
147
154
\textit{Exploiting Phone-class specific Landmarks for Refinement of Segment Boundaries in TTS Databases}, in Proceedings of INTERSPEECH, 2011, Florence
148
155
149
-
\item Hema A. Murthy,et al,
150
-
\textit{Building Unit Selection Speech Synthesizers in Indian Languages: An Initiative by Indian Consortium}, In Proceedings of Oriental COCOSDA, 2010, Kathmandu, Nepal
151
-
152
-
\item Veera Raghavendra Elluru, \textbf{Vijayaditya Peddinti} and Kishore Prahallad.
153
-
\textit{Speech Synthesis using Artifical Neural Networks}, in Proceedings of National Conference on Communications (NCC), 2010, Chennai, India
154
156
\end{enumerate}
155
157
\section{\sc Research and Industrial Experience}
156
158
@@ -188,46 +190,14 @@ \section{\sc Research and Industrial Experience}
188
190
Funded By Ministry of Commn. \& Info. Tech., India (MCIT)\\
189
191
&Involved in the development of a text-to-speech (TTS) synthesizer for Telugu. Developed an algorithm for automatic segmentation of audio databases (published in Interspeech, 2011) and designed a back-off strategy for missing units (published in ICASSP,2011), implementation syllable based synthesizer in the Festival framework.\\
190
192
&\\
191
-
&\textit{Indian Language Data Collection} ,
193
+
&\textit{Indian Language Data Collection} ,
192
194
Funded by Lang. Data Consortium of Indian Languages (LDC-IL)\\
193
195
&Worked on automatic generation of phonetic alignments of audio data with erroneous transcripts, for speech data in Telugu as part of project for the collection of speech data each in Telugu, Kannada and English languages.\\
194
196
195
197
&\\
196
198
\textbf{Jul '07--Jul '08} & \textbf{Technical Associate at Techmahindra Ltd.} \\
197
199
\end{longtable}
198
200
199
-
\section{\sc Teaching Experience}
200
-
201
-
\begin{tabular}{@{}p{0.4in}p{0.5in}p{4in}}
202
-
Spring & 2013 & Teaching Assistant, Speech and audio processing by humans and machines\\
203
-
\\
204
-
Fall & 2012,2013 & Teaching Assistant, Processing of audio and visual signals\\
205
-
\end{tabular}
206
-
207
-
208
-
\section{\sc Graduate Coursework}
209
-
210
-
\begin{tabular}{@{}p{2.3in}p{3in}}
211
-
\begin{list1}
212
-
\item Speech and audio processing by humans and machines
213
-
\item Information Extraction
214
-
\item Matrix Analysis
215
-
\item Random Signal Analysis
216
-
\item Machine Learning in Complex Domains
217
-
218
-
219
-
\end{list1}
220
-
&
221
-
\begin{list1}
222
-
\item Processing of audio and visual signals
223
-
\item Wavelets and Filter Banks
224
-
\item Computational Molecular Medicine (Techniques for Pattern Recognition in low data scenarios)
0 commit comments