We train a bank of complex filters that operates on the raw waveform and is
fed into a convolutional neural network for end-to-end phone recognition. These
time-domain filterbanks (TD-filterbanks) are initialized as an approximation of
mel-filterbanks, and then fine-tuned jointly with the remaining convolutional
architecture. We perform phone recognition experiments on TIMIT and show that
for several architectures, models trained on TD-filterbanks consistently
outperform their counterparts trained on comparable mel-filterbanks. We get our
best performance by learning all front-end steps, from pre-emphasis up to
averaging. Finally, we observe that the filters at convergence have an
asymmetric impulse response, and that some of them remain almost analytic.

通过对原始波形进行滤波及卷积神经网络训练，使得时域滤波器组近似于 Mel 滤波器组，并在 TIMIT 上的电话号码识别实验中，相较于使用 Mel 滤波器的模型，TD-filterbanks 在多个架构上均表现优异，这些滤波器在收敛时具有非对称脉冲响应，且一些滤波器几乎保持解析的情况。