A ResNet-50-Based Convolutional Neural Network Model for Language ID Identification from Speech Recordings
Celano Giuseppe
Abstract
This paper describes the model built for the SIGTYP 2021 Shared Task aimed at identifying 18 typologically different languages from speech recordings. Mel-frequency cepstral coefficients derived from audio files are transformed into spectrograms, which are then fed into a ResNet-50-based CNN architecture. The final model achieved validation and test accuracies of 0.73 and 0.53, respectively.
Topics & Concepts
SpectrogramComputer scienceConvolutional neural networkSpeech recognitionResidual neural networkMel-frequency cepstrumTask (project management)Artificial intelligenceIdentification (biology)Natural language processingArtificial neural networkFeature extractionPattern recognition (psychology)EngineeringSystems engineeringBotanyBiologySpeech Recognition and SynthesisMusic and Audio ProcessingNatural Language Processing Techniques