Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
read the original abstract
Describes an audio dataset of spoken words designed to help train and evaluate keyword spotting systems. Discusses why this task is an interesting challenge, and why it requires a specialized dataset that is different from conventional datasets used for automatic speech recognition of full sentences. Suggests a methodology for reproducible and comparable accuracy metrics for this task. Describes how the data was collected and verified, what it contains, previous versions and properties. Concludes by reporting baseline results of models trained on this dataset.
This paper has not been read by Pith yet.
Forward citations
Cited by 57 Pith papers
-
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Mamba is a linear-time sequence model using input-dependent selective SSMs that achieves SOTA results across modalities and matches twice-larger Transformers on language modeling with 5x higher inference throughput.
-
Efficiently Modeling Long Sequences with Structured State Spaces
S4 is an efficient state space sequence model that captures long-range dependencies via structured parameterization of the SSM, achieving state-of-the-art results on the Long Range Arena and other benchmarks while bei...
-
DiffWave: A Versatile Diffusion Model for Audio Synthesis
DiffWave is a non-autoregressive diffusion model that generates high-fidelity audio waveforms from noise in constant steps, matching WaveNet vocoder quality while being orders of magnitude faster and outperforming pri...
-
LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning
LongSpike integrates fractional-order state-space modeling into spiking neural networks, enabling better long-sequence performance than prior SNNs on LRA, WikiText-103, and Speech Commands benchmarks while retaining s...
-
Attention by Synchronization in Coupled Oscillator Networks
Kuramoto synchronization dynamics implement a provably unique and globally attractive attention mechanism that replaces softmax for physical substrates and shows competitive empirical performance.
-
Totoro$^+$: An Adaptive and Scalable Edge Federated Learning System
Totoro+ is a DHT-based fully decentralized FL system with locality-aware multi-ring P2P structure, pub/sub forest, and game-theoretic path planning that claims O(log N) hops and 1.2-14x speedup for many concurrent app...
-
FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping
FiTS spiking neurons improve auditory task performance over LIF baselines by factorizing computation into frequency selectivity and group-delay-based temporal shaping, yielding interpretable per-neuron parameters.
-
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
Cumulative state updates in CMRU restore gradient flow through time in quantized bistable RNNs, yielding more stable convergence and competitive or superior performance versus LRUs and minGRUs on long-range sequence tasks.
-
End-to-End Keyword Spotting on FPGA Using Graph Neural Networks with a Neuromorphic Auditory Sensor
An FPGA implementation of a neuromorphic auditory sensor plus graph neural network achieves 87.43% accuracy on Google Speech Commands v2 with sub-35 µs latency and 1.12 W power.
-
MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models
MMEB-V3 benchmark shows omni-modality embedding models fail to enforce instruction-specified modality constraints and exhibit asymmetric, query-biased retrieval.
-
Covariance Estimation for Matrix-variate Data via Fixed-rank Core Covariance Geometry
The space of rank-r core covariances forms a smooth manifold except on a measure-zero set, enabling a partial-isotropy shrinkage estimator for matrix-variate data.
-
DASB - Discrete Audio and Speech Benchmark
DASB is a new benchmark for discrete audio tokens showing semantic tokens outperform acoustic ones but discrete representations remain less robust than continuous features across domains.
-
Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications
Wake Vision pipeline produces a 6M-image person detection dataset for TinyML with 2.2% label error, improving model accuracy up to 6.6% over prior VWW benchmark across architectures and subsets.
-
End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users
An end-to-end SLU architecture with frozen SSL acoustic encoder, LSTM classification head, and cross-modal distillation achieves 93% accuracy on simple commands and 82% on spontaneous speech at 7 ms latency on the new...
-
Exploiting Neural Audio Codec Latents for Adversarial Audio Attacks
A conditional generator operating in neural audio codec latent space produces targeted adversarial audio examples in one forward pass, reaching up to 99% success rate at sub-7 ms inference.
-
Adaptive Speech-to-Spike Encoding for Spiking Neural Networks
A learnable residual speech-to-spike encoder jointly trained with an R-LIF SNN achieves up to 94.97% accuracy on GSC-v2 with a 35k-parameter model and supports DFA credit assignment at 91.5%.
-
NeuralMUSIC: A Hybrid Neural-Subspace Framework for Robot Sound Source Localization
NeuralMUSIC combines neural covariance estimation with the MUSIC pipeline, frequency attention fusion, and self-supervised learning to improve direction-of-arrival estimation for robotic sound source localization.
-
Representation Matters in Randomized Smoothing for Audio Classification
Randomized smoothing in audio classification requires explicit specification of the certified representation and preprocessing because different choices produce different certified accuracies and effective perturbatio...
-
What changes after deployment? A survey on On-device Learning in TinyML
A survey of on-device learning in TinyML organized by distribution change regimes, highlighting influences on applications, hardware, and solutions plus a gap between benchmarks and deployments.
-
Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier
Plug-in losses approximate EDL training objectives at the Dirichlet mean with decaying error as evidence grows, including softmax under a specific mapping, and match classical EDL performance on Google Speech Commands.
-
AudioMosaic: Contrastive Masked Audio Representation Learning
AudioMosaic learns general-purpose audio representations through contrastive pre-training with structured spectrogram masking, reaching state-of-the-art results on standard benchmarks and improving audio-language tasks.
-
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations
BMRUs enable a direct one-to-one mapping from learned parameters to current-mode analog circuit elements, with discrete hysteretic outputs suppressing noise by at least 20x and supporting sub-microwatt RNN inference i...
-
EdgeSpike: Spiking Neural Networks for Low-Power Autonomous Sensing in Edge IoT Architectures
EdgeSpike delivers 91.4% mean accuracy on five sensing tasks with 31x lower energy on neuromorphic hardware and 6.3x longer battery life in a seven-month field deployment compared to conventional CNNs.
-
ComMark: Covert and Robust Black-Box Model Watermarking with Compressed Samples
ComMark embeds covert watermarks in models using frequency-domain compressed samples and simulated attacks, claiming state-of-the-art covertness and robustness across image, speech, text, and video tasks.
-
AaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformers
AaSP learns aliasing-stable audio representations by augmenting patch tokens with adaptive subband features from alias-prone bands and using teacher-student masked modeling plus multi-mask contrastive regularization, ...
-
SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
SiLIF models apply SSM dynamics and parametrization to spiking neurons for stable training, reaching new SOTA on event-based and raw-audio speech datasets while using half the compute of SSMs via synaptic delays.
-
Simplified State Space Layers for Sequence Modeling
S5 uses a single MIMO state space model with S4-derived initialization to match S4 efficiency and reach 87.4% average accuracy on the Long Range Arena benchmark.
-
Sub-band Convolutional Neural Networks for Small-footprint Spoken Term Classification
Sub-band CNN applies distinct kernels per frequency sub-band to reduce computation 39.7-49.3% versus full-band CNN on Speech Commands dataset while maintaining accuracy.
-
Federated Learning with Non-IID Data
Non-IID data causes up to 55% accuracy loss in federated learning due to weight divergence measured by earth mover's distance; 5% globally shared data recovers 30% accuracy on CIFAR-10.
-
Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attack
Pmeta-TLA combines a frame-level timbre leakage trigger with meta-learning and PCGrad to inject multiple backdoors into speech models in one training run, claiming better attack success, stealth, and lower cost than b...
-
Personalized Keyword Spotting for User-Defined Keywords Leveraging Text-Independent Speaker Verification
ZP-KWS combines a phoneme-supervised audio encoder with a 0.9M-parameter GE2E speaker encoder and multiplicative late fusion to cut target-only FRR at 1% FAR by up to 60% on LibriPhrase, Google Speech Commands, and Qu...
-
Learning task-specific subspaces via interventional post-training of speech foundation models
Interventional contrastive learning applied after pre-training disentangles speaker and content information in speech foundation model embeddings, yielding better out-of-domain speaker verification.
-
Representation Matters in Randomized Smoothing for Audio Classification
Randomized smoothing robustness certification in audio is under-specified without explicit choice of certified object, preprocessing policy, and perturbation model, as different representations yield different certifi...
-
Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals
A continuous-token model with shared Haar wavelet coefficients reports 39.92 dB audio, 29.37 dB image, and 23.93 dB video PSNR on three datasets and shows energy-based selection outperforms uniform selection by roughly 16 dB.
-
Effective User-defined Keyword Spotting with Dual-stage Matching, Multi-modal Enrollment, and Continual Adaptation
DMA-KWS achieves 97.85% AUC and 6.13% EER on LibriPhrase Hard via dual-stage CTC/QbyT matching, multi-modal enrollment, and lightweight continual adaptation with 187k parameters.
-
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations
BMRUs enable analog recurrent neural network hardware via discrete outputs that suppress noise 20-fold, with one-to-one parameter-to-circuit mapping and linear power scaling for recurrence.
-
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
CMRU restores gradient flow in BMRU via cumulative state updates with skip-connections through time, yielding better convergence and benchmark performance while retaining quantized persistent memory.
-
ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantization
ShiftLIF maps membrane potentials to logarithmically spaced power-of-two spike levels, improving representational capacity in SNNs while keeping synaptic operations multiplier-free.
-
From Cortical Synchronous Rhythm to Brain Inspired Learning Mechanism: An Oscillatory Spiking Neural Network with Time-Delayed Coordination
S2-Net is an oscillatory spiking neural network that uses time-delayed synchronization for bottom-up and top-down coordination to enable efficient, brain-inspired information processing across tasks like decoding and ...
-
ULTRAS -- Unified Learning of Transformer Representations for Audio and Speech Signals
ULTRAS unifies audio and speech representation learning in a single transformer by applying patch masking to log-mel spectrograms and using a joint spectral-temporal prediction loss.
-
How Class Ontology and Data Scale Affect Audio Transfer Learning
Larger pre-training data scale and class diversity improve audio transfer learning performance, yet similarity between pre-training and target task has a stronger positive effect.
-
Prototype-Guided Robust Learning against Backdoor Attacks
PGRL defends ML models from backdoor attacks by using a few verified clean samples to guide removal of suspicious training data and unlearning of backdoor features during fine-tuning, outperforming prior defenses in e...
-
Towards Debugging Deep Neural Networks by Generating Speech Utterances
Activation maximization applied to a speech command DNN, followed by WaveNet synthesis, produces class-specific utterances that human evaluators can interpret, supporting its use for model debugging.
-
DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning
DRL-CLBA applies DDPG reinforcement learning and deep audio steganography to create sample-specific clean-label backdoor attacks on speech DNNs that resist fine-tuning, pruning, and spectral signature defenses.
-
Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System
Clustering DINO representations via K-means and LDA filters poisoned speech samples, reducing attack success rate from 99.75% to 0.25% at 10% poisoning level.
-
WQ-Fusion: Dynamic Gated Attention for Cross-Domain Audio Representation
WQ-Fusion combines Whisper and Qwen encoders with gated attention to reach 0.836 on the Interspeech 2026 Audio Encoder Capability Challenge, outperforming single-encoder baselines.
-
NeuralMUSIC: A Hybrid Neural-Subspace Framework for Robot Sound Source Localization
Hybrid framework estimates covariance via neural net then runs MUSIC with frequency attention fusion and self-supervised pretraining for robot sound source localization.
-
Positional Encoding in the Context of Memristor-Based Analog Computation for Automatic Speech Recognition
Modifying ADC bit precision for positional encoding layers in memristor analog ASR computation reduces degradation by up to 50% relative.
-
Design principles for optoelectronic light-scattering reservoir computing at the edge of chaos
Authors map reservoir dynamics, input coupling, and interconnectivity in a light-scattering optoelectronic reservoir to locate quantitative optima that yield stable Mackey-Glass prediction and 84.5% accuracy on spoken...
-
minAction.net: Energy-First Neural Architecture Design -- From Biological Principles to Systematic Validation
Large-scale experiments show architecture performance depends on task type, not universality, and a single-parameter energy penalty reduces computational energy by ~1000x with negligible accuracy cost.
-
Whisper-AuT: Domain-Adapted Audio Encoder for Efficient Audio-LLM Training
Whisper-AuT is a domain-adapted audio encoder obtained by fine-tuning Whisper-large-v3 on mixed speech, environmental, and music data, yielding gains of +23% on ESC-50, +5% on GTZAN, and +0.7% on Speech Commands.
-
Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing
Bayesian weight learning in surrogate-gradient SNNs smooths the loss landscape and improves negative log-likelihood plus Brier score on Heidelberg Digits and Speech Commands datasets.
-
Keyword Spotting for Hearing Assistive Devices Robust to External Speakers
A multi-task deep residual network jointly performs keyword spotting and own-voice detection, delivering around 32% relative KWS accuracy gain on a hearing-aid-emulated corpus derived from Google Speech Commands.
-
A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting
Joint training of speech enhancement and KWS with a novel CRN and Mel features improves noise robustness for small-footprint devices.
-
Attention Is not Everything: Efficient Alternatives for Vision
A survey that taxonomizes non-Transformer vision models and evaluates their practical trade-offs across efficiency, scalability, and robustness.
-
Embedded Machine Learning for Microcontroller-Class Edge Devices: Data, Feature, Evaluation, and Deployment Pipelines
This paper outlines a systems-oriented workflow for embedded machine learning on microcontrollers, using accelerometer-based motion recognition and audio keyword spotting as running examples to illustrate data, featur...
-
Keyword spotting using convolutional neural network for speech recognition in Hindi
CNNs using MFCC features achieve 91.79% accuracy for keyword spotting in Hindi speech on a 40,000-sample dataset.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.