End-to-end Language Identification Using Multi-head Self-attention And 1D Convolutional Neural Networks

Abstract

In this work, we propose a new approach for language identification using multi-head self-attention combined with raw waveform based 1D convolutional neural networks for Indian languages. Our approach uses an encoder, multi-head selfattention, and a statistics pooling layer. The encoder learns features directly from raw waveforms using 1D convolution kernels and an LSTM layer. The LSTM layer captures temporal information between the features extracted by the 1D convolutional layer. The multi-head self-attention layer takes outputs of the LSTM layer and applies self-attention mechanisms on these features with M different heads. This process helps the model give more weightage to the more useful features and less weightage to the less relevant features. Finally, the frame-level features are combined using a statistics pooling layer to extract the utterance-level feature vector label prediction. We conduct all our experiments on the 373 hrs of audio data for eight different Indian languag

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyn2021end

Related papers

• Utterance-level End-to-end Language Identification Using Attention-based CNN-BLSTM (2019)11.67
• Multi-language Identification Using Convolutional Recurrent Neural Network (2016)13.88
• Spoken Language Identification Using Convnets (2019)9.59
• Improved Language Identification Through Cross-lingual Self-supervised Learning (2021)10.61
• Joint Language Identification Of Code-switching Speech Using Attention Based E2E Network (2019)5.24
• State-of-the-art Speech Recognition Using Multi-stream Self-attention With Dilated 1D Convolutions (2019)11.93
• Self Multi-head Attention For Speaker Recognition (2019)13.84
• Streaming End-to-end Bilingual ASR Systems With Joint Language Identification (2020)0.00