Role of non-linear data processing on speech recognition task in the framework of reservoir computing
This work addresses the benchmarking challenge for neuromorphic hardware in speech recognition, helping researchers isolate hardware performance from data preprocessing effects.
The study quantified the separate contributions of acoustic transformations and neuromorphic hardware to speech recognition success rates, showing that non-linearity in acoustic transformations is critical for feature extraction and that reservoir computing devices provide measurable gains in word success rates.
The reservoir computing neural network architecture is widely used to test hardware systems for neuromorphic computing. One of the preferred tasks for bench-marking such devices is automatic speech recognition. However, this task requires acoustic transformations from sound waveforms with varying amplitudes to frequency domain maps that can be seen as feature extraction techniques. Depending on the conversion method, these may obscure the contribution of the neuromorphic hardware to the overall speech recognition performance. Here, we quantify and separate the contributions of the acoustic transformations and the neuromorphic hardware to the speech recognition success rate. We show that the non-linearity in the acoustic transformation plays a critical role in feature extraction. We compute the gain in word success rate provided by a reservoir computing device compared to the acoustic transformation only, and show that it is an appropriate benchmark for comparing different hardware. Finally, we experimentally and numerically quantify the impact of the different acoustic transformations for neuromorphic hardware based on magnetic nano-oscillators.