Titlebook: Speech and Computer; 22nd International C Alexey Karpov,Rodmonga Potapova Conference proceedings 2020 Springer Nature Switzerland AG 2020 a

Dawdle

Automated Destructive Behavior State Detection on the 1D CNN-Based Voice Analysis,tion to this problem is an integral part of the project to create a unified socio-cyberphysical system for managing Internet content in order to identify destructive materials and protect network users.

小鹿

Lightweight CNN for Robust Voice Activity Detection,itecture in noisy conditions. The resulting network obtains 62.6% relative improvements in EER compared to a deep feedforward neural network (DNN) of comparable parameter count on a noisy test dataset.

犬儒主義者

Automatic Information Extraction from Scanned Documents,age deskewing. Optical Character Recognition solutions and approaches to information extraction are compared using the whole system performance. The best performance of information extraction with the database was obtained by the Locality-sensitive Hashing algorithm.

評(píng)論者

無能性

,Exploration of End-to-End ASR for OpenSTT – Russian Open Speech-to-Text Dataset,h the strong hybrid ASR system based on LF-MMI TDNN-F acoustic model..For the three available validation sets (phone calls, YouTube, and books), our best end-to-end model achieves word error rate (WER) of 34.8%, 19.1%, and 18.1%, respectively. Under the same conditions, the hybrid ASR system demonstrates 33.5%, 20.9%, and 18.6% WER.

companion

A Rumor Detection in Russian Tweets,llection contains rumors of three events. The software for rumor detection in tweets was developed. We used SVM to filter tweets by type of speech act. An experiment was conducted to check the tweet for rumor with a calculation of accuracy, precision and recall values. F1 measure reached the value 0.91.

nugatory

高度

Speech Emotion Recognition Using Spectrogram Patterns as Features, classifier is then trained with features obtained from the extracted patterns. Our experimental evaluations indicate that the spectrogram-based patterns outperform the standard set of acoustic features. It is also shown that the results can further be improved with the increasing number of spectrogram partitions.

確認(rèn)

milligram

Toxicity in Texts and Images on the Internet, there was trained a neural network that inferred labels for unannotated pictures. Neural network layer activations for these images were clustered and manually classified to find the most typical ways of expressing aggression in images. We find that racial stereotypes are the main cause of toxicity in images (.).