Method forward

encoder/model.py:41–61

Computes the embeddings of a batch of utterance spectrograms. :param utterances: batch of mel-scale filterbanks of same duration as a tensor of shape (batch_size, n_frames, n_channels) :param hidden_init: initial hidden state of the LSTM as a tensor of sha

(self, utterances, hidden_init=None)

        clip_grad_norm_(self.parameters(), 3, norm_type=2)
    
    def forward(self, utterances, hidden_init=None):
        """
        Computes the embeddings of a batch of utterance spectrograms.
        
        :param utterances: batch of mel-scale filterbanks of same duration as a tensor of shape 
        (batch_size, n_frames, n_channels) 
        :param hidden_init: initial hidden state of the LSTM as a tensor of shape (num_layers, 
        batch_size, hidden_size). Will default to a tensor of zeros if None.
        :return: the embeddings as a tensor of shape (batch_size, embedding_size)
        """
        # Pass the input through the LSTM layers and retrieve all outputs, the final hidden state
        # and the final cell state.
        out, (hidden, cell) = self.lstm(utterances, hidden_init)
        
        # We take only the hidden state of the last layer
        embeds_raw = self.relu(self.linear(hidden[-1]))
        
        # L2-normalize it
        embeds = embeds_raw / (torch.norm(embeds_raw, dim=1, keepdim=True) + 1e-5)        

        return embeds
    
    def similarity_matrix(self, embeds):
        """