|
|
|
|
|
Pau Baquero-Arnal, Javier Jorge, Adrià Giménez, Javier Iranzo-Sánchez, Alejandro Pérez, Gonçal Vicent Garcés Díaz-Munío, Joan Albert Silvestre-Cerdà, Jorge Civera, Albert Sanchis and Alfons Juan
This work has direct application in live automatic captioning of audiovisual material, which is fundamental in accessibility.
|
|
|
|
|
|
|
|
|
|
|
Xintong Wang and Chuangang Zhao
Recent research shows recurrent neural network-Transducer (RNN-T) architecture has become a mainstream approach for streaming speech recognition. In this work, we investigate the VGG2 network as the input layer to the RNN-T in streaming speech recognitio...
ver más
|
|
|
|
|
|
|
|
|
|
|
Nikolaos Vryzas, Nikolaos Tsipas and Charalampos Dimoulas
Radio is evolving in a changing digital media ecosystem. Audio-on-demand has shaped the landscape of big unstructured audio data available online. In this paper, a framework for knowledge extraction is introduced, to improve discoverability and enrichmen...
ver más
|
|
|
|
|
|