279 results on '"Georges Linarès"'
Search Results
102. Constrained speaker diarization of TV series based on visual patterns.
103. Quaternion Recurrent Neural Networks.
104. Audiovisual speaker diarization of TV series.
105. Quaternion Convolutional Neural Networks for Heterogeneous Image Processing.
106. Speech recognition with quaternion neural networks.
107. Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognition.
108. D{é}tection de locuteurs dans les s{é}ries TV.
109. Combination of probabilistic and possibilistic language models.
110. A language-identification inspired method for spontaneous speech detection.
111. Improving back-off models with bag of words and hollow-grams.
112. Classification du genre vidéo reposant sur des transcriptions automatiques.
113. Semantic cache model driven speech recognition.
114. On-the-fly video genre classification by combination of audio features.
115. Transcription-based video genre classification.
116. Audio-Based Video Genre Identification.
117. Compact Multiview Representation of Documents Based on the Total Variability Space.
118. Probabilistic and possibilistic language models based on the world wide web.
119. Robust audio-based classification of video genre.
120. Factor analysis for audio-based video genre classification.
121. Combined low level and high level features for out-of-vocabulary word detection.
122. On-demand new word learning using world wide web.
123. Generalized driven decoding for speech recognition system combination.
124. Frame-based acoustic feature integration for speech understanding.
125. On-the-fly term spotting by phonetic filtering and request-driven decoding.
126. Text island spotting in large speech databases.
127. Fast adaptation of GMM-based compact models.
128. System Combination by Driven Decoding.
129. The LIA Speech Recognition System: From 10xRT to 1xRT.
130. Fast Discriminant Training of Semi-continuous HMM.
131. Scalable language model look-ahead for LVCSR.
132. Reducing computational and memory cost for cellular phone embedded speech recognition system.
133. Ajout de nouveaux noms propres au vocabulaire d'un système de transcription en utilisant un corpus diachronique.
134. Feature selection using Principal Component Analysis for massive retweet detection.
135. Web-based possibilistic language models for automatic speech recognition.
136. Structural linear model-space transformations for speaker adaptation.
137. Structural speaker adaptation using maximum a posteriori approach and a Gaussian distributions merging technique.
138. Automatic Text Summarization Approaches to Speed up Topic Model Learning Process.
139. Parallel Long Short-Term Memory for Multi-stream Classification.
140. Phoneme Lattice Based A* Search Algorithm for Speech Recognition.
141. Dynamic Combination of Automatic Speech Recognition Systems by Driven Decoding.
142. A posteriori and a priori transformations for speaker adaptation in large vocabulary speech recognition systems.
143. Integrating imperfect transcripts into speech recognition systems for building high-quality corpora.
144. Modeling nuisance variabilities with factor analysis for GMM-based audio pattern classification.
145. Processing and transcribing spontaneous speech.
146. Automatic alignment and phonetic studies: Comparing alignment systems for the analysis of the schwa.
147. Model Breaking Detection Using Independent Component Classifier.
148. Mixed acoustic events classification using ICA and subspace classifier.
149. LIA @ MediaEval 2013 Spoken Web Search Task: An I-Vector based Approach.
150. LIA @ MediaEval 2013 Crowdsourcing Task: Metadata or not Metadata? That is a Fashion Question.
Catalog
Books, media, physical & digital resources
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.