# Trainable Frontend For Robust and Far-Field Keyword Spotting

arXiv: https://arxiv.org/abs/1607.05666 · HTML: https://mlsanity.com/paper/1607.05666/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2016.

## Built on by (most cited first, 30 of 33)

- [LEAF: A Learnable Frontend for Audio Classification](https://mlsanity.com/paper/2101.08596/) (2021)
- [Deep Spoken Keyword Spotting: An Overview](https://mlsanity.com/paper/2111.10592/) (2021)
- [BIRB: A Generalization Benchmark for Information Retrieval in Bioacoustics](https://mlsanity.com/paper/2312.07439/) (2023)
- [Real-time Denoising and Dereverberation with Tiny Recurrent U-Net](https://mlsanity.com/paper/2102.03207/) (2021)
- [Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification](https://mlsanity.com/paper/2206.12513/) (2022)
- [HeAR -- Health Acoustic Representations](https://mlsanity.com/paper/2403.02522/) (2024)
- [Visual Keyword Spotting with Attention](https://mlsanity.com/paper/2110.15957/) (2021)
- [Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows](https://mlsanity.com/paper/2201.07677/) (2022)
- [EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use](https://mlsanity.com/paper/2207.05508/) (2022)
- [Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization](https://mlsanity.com/paper/2111.06531/) (2021)
- [Learning Temporal Resolution in Spectrogram for Audio Classification](https://mlsanity.com/paper/2210.01719/) (2022)
- [Sound Event Detection in Urban Audio With Single and Multi-Rate PCEN](https://mlsanity.com/paper/2102.03468/) (2021)
- [Segment-level Metric Learning for Few-shot Bioacoustic Event Detection](https://mlsanity.com/paper/2207.07773/) (2022)
- [Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices](https://mlsanity.com/paper/2105.11856/) (2021)
- [Optimized Power Normalized Cepstral Coefficients towards Robust Deep Speaker Verification](https://mlsanity.com/paper/2109.12058/) (2021)
- [An Overview of Indian Spoken Language Recognition from Machine Learning Perspective](https://mlsanity.com/paper/2212.03812/) (2022)
- [TACNET: Temporal Audio Source Counting Network](https://mlsanity.com/paper/2311.02369/) (2023)
- [Parameterized Channel Normalization for Far-field Deep Speaker Verification](https://mlsanity.com/paper/2109.12056/) (2021)
- [Learnable Nonlinear Compression for Robust Speaker Verification](https://mlsanity.com/paper/2202.05236/) (2022)
- [Learning neural audio features without supervision](https://mlsanity.com/paper/2203.15519/) (2022)
- [Spot keywords from very noisy and mixed speech](https://mlsanity.com/paper/2305.17706/) (2023)
- [Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles](https://mlsanity.com/paper/2310.11379/) (2023)
- [Deep Learning-Based Acoustic Mosquito Detection in Noisy Conditions Using Trainable Kernels and Augmentations](https://mlsanity.com/paper/2207.13843/) (2022)
- [Studying the Effect of Audio Filters in Pre-Trained Models for Environmental Sound Classification](https://mlsanity.com/paper/2408.13644/) (2024)
- [Biomimetic Frontend for Differentiable Audio Processing](https://mlsanity.com/paper/2409.08997/) (2024)
- [Unsupervised Domain Adaptation Via Data Pruning](https://mlsanity.com/paper/2409.12076/) (2024)
- [Improving Distribution Alignment with Diversity-based Sampling](https://mlsanity.com/paper/2410.04235/) (2024)
- [EdgeSpot: Efficient and High-Performance Few-Shot Model for Keyword Spotting](https://mlsanity.com/paper/2601.16316/) (2026)
- [Spectrogram features for audio and speech analysis](https://mlsanity.com/paper/2603.14917/) (2026)
- [Cross-Cultural Bias in Mel-Scale Representations: Evidence and Alternatives from Speech and Music](https://mlsanity.com/paper/2604.10503/) (2026)

## Abstract (arXiv)

Robust and far-field speech recognition is critical to enable true hands-free communication. In far-field conditions, signals are attenuated due to distance. To improve robustness to loudness variation, we introduce a novel frontend called per-channel energy normalization (PCEN). The key ingredient of PCEN is the use of an automatic gain control based dynamic compression to replace the widely used static (such as log or root) compression. We evaluate PCEN on the keyword spotting task. On our large rerecorded noisy and far-field eval sets, we show that PCEN significantly improves recognition performance. Furthermore, we model PCEN as neural network layers and optimize high-dimensional PCEN parameters jointly with the keyword spotting acoustic model. The trained PCEN frontend demonstrates significant further improvements without increasing model complexity or inference-time cost.