# Very Deep Convolutional Neural Networks for Raw Waveforms

arXiv: https://arxiv.org/abs/1610.00087 · HTML: https://mlsanity.com/paper/1610.00087/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2016.

## Built on by (most cited first, 30 of 68)

- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [CKConv: Continuous Kernel Convolution For Sequential Data](https://mlsanity.com/paper/2102.02611/) (2021)
- [MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic](https://mlsanity.com/paper/2205.06900/) (2022)
- [Survey: Transformer based Video-Language Pre-training](https://mlsanity.com/paper/2109.09920/) (2021)
- [NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems](https://mlsanity.com/paper/2304.04640/) (2023)
- [Defending against Adversarial Audio via Diffusion Model](https://mlsanity.com/paper/2303.01507/) (2023)
- [Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer](https://mlsanity.com/paper/2112.08995/) (2021)
- [MEA-Defender: A Robust Watermark against Model Extraction Attack](https://mlsanity.com/paper/2401.15239/) (2024)
- [TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification](https://mlsanity.com/paper/2309.11845/) (2023)
- [Multi-view Audio and Music Classification](https://mlsanity.com/paper/2103.02420/) (2021)
- [Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data](https://mlsanity.com/paper/2202.00097/) (2022)
- [Keyword localisation in untranscribed speech using visually grounded speech models](https://mlsanity.com/paper/2202.01107/) (2022)
- [A Hybrid SFANC-FxNLMS Algorithm for Active Noise Control based on Deep Learning](https://mlsanity.com/paper/2208.08082/) (2022)
- [Sparse learned kernels for interpretable and efficient medical time series processing](https://mlsanity.com/paper/2307.05385/) (2023)
- [WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm](https://mlsanity.com/paper/2101.05478/) (2021)
- [A Functional Information Perspective on Model Interpretation](https://mlsanity.com/paper/2206.05700/) (2022)
- [Deep Generative Fixed-filter Active Noise Control](https://mlsanity.com/paper/2303.05788/) (2023)
- [PosCUDA: Position based Convolution for Unlearnable Audio Datasets](https://mlsanity.com/paper/2401.02135/) (2024)
- [BiT-MamSleep: Bidirectional Temporal Mamba for EEG Sleep Staging](https://mlsanity.com/paper/2411.01589/) (2024)
- [Tiny Transformers for Environmental Sound Classification at the Edge](https://mlsanity.com/paper/2103.12157/) (2021)
- [Visually-aware Acoustic Event Detection using Heterogeneous Graphs](https://mlsanity.com/paper/2207.07935/) (2022)
- [What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement](https://mlsanity.com/paper/2303.11249/) (2023)
- [TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring](https://mlsanity.com/paper/2207.11290/) (2022)
- [Representation Learning for Appliance Recognition: A Comparison to Classical Machine Learning](https://mlsanity.com/paper/2209.03759/) (2022)
- [On-Device Domain Generalization](https://mlsanity.com/paper/2209.07521/) (2022)
- [jazznet: A Dataset of Fundamental Piano Patterns for Music Audio Machine Learning Research](https://mlsanity.com/paper/2302.08632/) (2023)
- [MSAT: Biologically Inspired Multi-Stage Adaptive Threshold for Conversion of Spiking Neural Networks](https://mlsanity.com/paper/2303.13080/) (2023)
- [LEAN: Light and Efficient Audio Classification Network](https://mlsanity.com/paper/2305.12712/) (2023)
- [Speech Understanding on Tiny Devices with A Learning Cache](https://mlsanity.com/paper/2311.18188/) (2023)
- [On the Promise for Assurance of Differentiable Neurosymbolic Reasoning Paradigms](https://mlsanity.com/paper/2502.08932/) (2025)

## Abstract (arXiv)

Learning acoustic models directly from the raw waveform data with minimal processing is challenging. Current waveform-based models have generally used very few (~2) convolutional layers, which might be insufficient for building high-level discriminative features. In this work, we propose very deep convolutional neural networks (CNNs) that directly use time-domain waveforms as inputs. Our CNNs, with up to 34 weight layers, are efficient to optimize over very long sequences (e.g., vector of size 32000), necessary for processing acoustic waveforms. This is achieved through batch normalization, residual learning, and a careful design of down-sampling in the initial layers. Our networks are fully convolutional, without the use of fully connected layers and dropout, to maximize representation learning. We use a large receptive field in the first convolutional layer to mimic bandpass filters, but very small receptive fields subsequently to control the model capacity. We demonstrate the performance gains with the deeper models. Our evaluation shows that the CNN with 18 weight layers outperform the CNN with 3 weight layers by over 15% in absolute accuracy for an environmental sound recognition task and matches the performance of models using log-mel features.