Google Speech Commands
Canonical35papers using it
2021first seen
The 'Google Speech Commands' dataset contains a collection of spoken commands used to evaluate keyword spotting performance in speech recognition systems.
Papers using Google Speech Commands (35)
- Few-shot Open-set Learning For On-device Customization Of Keyword Spotting SystemsKeyword Mamba: Spoken Keyword Spotting with State Space ModelsLLM-Synth4KWS: Scalable Automatic Generation and Synthesis of Confusable Data for Custom Keyword SpottingFrom Physics to Representation: Audio Learning with Synthetic Pre-training via Procedural GenerationPractical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape SmoothingWhisper-AuT: Domain-Adapted Audio Encoder for Efficient Audio-LLM TrainingWaveSSM: Multiscale State-Space Models for Non-stationary Signal AttentionSW-ASR: A Context-Aware Hybrid ASR Pipeline for Robust Single Word Speech RecognitionSpeech Command Recognition Using LogNNet Reservoir Computing for Embedded SystemsText-Aware Adapter for Few-Shot Keyword SpottingReparameterized Multi-resolution Convolutions For Long Sequence ModellingDiagonal State Spaces are as Effective as Structured State SpacesDataset Condensation via Efficient Synthetic-Data ParameterizationClassical-to-Quantum Transfer Learning for Spoken Command Recognition
Based on Quantum Neural NetworksA Separable Temporal Convolution Neural Network with Attention for
Small-Footprint Keyword SpottingImplicit Acoustic Echo Cancellation for Keyword Spotting and
Device-Directed Speech DetectionCombination of Time-domain, Frequency-domain, and Cepstral-domain
Acoustic Features for Speech Commands ClassificationFilterbank Learning for Noise-Robust Small-Footprint Keyword SpottingSelf-supervised speech representation learning for keyword-spotting with
light-weight transformersContrastive Speech Mixup for Low-resource Keyword SpottingBoosting keyword spotting through on-device learnable user speech
characteristicsExploiting Hybrid Models of Tensor-Train Networks for Spoken Command
RecognitionSpeech Augmentation Based Unsupervised Learning for Keyword SpottingDamage Control During Domain Adaptation for Transducer Based Automatic
Speech RecognitionGAN You Hear Me? Reclaiming Unconditional Speech Synthesis from
Diffusion ModelsMAST: Multiscale Audio Spectrogram TransformersSpot keywords from very noisy and mixed speechFew-Shot Open-Set Learning for On-Device Customization of KeyWord
Spotting SystemsImproving vision-inspired keyword spotting using dynamic module skipping
in streaming conformer encoderVIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make
Keyword Spotting More Robust Against Adversarial AttacksDifferential Evolution Algorithm based Hyper-Parameters Selection of
Convolutional Neural Network for Speech Command RecognitionFew-Shot Keyword Spotting from Mixed SpeechReparameterized Multi-Resolution Convolutions for Long Sequence
ModellingEnhancing Synthetic Training Data for Speech Commands: From ASR-Based
Filtering to Domain Adaptation in SSL Latent SpaceConvolutional Variational Autoencoders for Spectrogram Compression in
Automatic Speech Recognition