Keyword Spotting

39 papers with code • 7 benchmarks • 5 datasets

In speech processing, keyword spotting deals with the identification of keywords in utterances.

( Image credit: Simon Grest )

Latest papers without code

Broadcasted Residual Learning for Efficient Keyword Spotting

8 Jun 2021

We present a broadcasted residual learning method to achieve high accuracy with small model size and computational load.

Keyword Spotting

Teaching keyword spotters to spot new keywords with limited examples

4 Jun 2021

Towards easily customizable KWS models, we present KeySEM (Keyword Speech EMbedding), a speech embedding model pre-trained on the task of recognizing a large number of keywords.

Keyword Spotting

Noisy student-teacher training for robust keyword spotting

3 Jun 2021

We propose self-training with noisy student-teacher approach for streaming keyword spotting, that can utilize large-scale unlabeled data and aggressive data augmentation.

Data Augmentation Keyword Spotting

A Streaming End-to-End Framework For Spoken Language Understanding

20 May 2021

In this paper, we propose a streaming end-to-end framework that can process multiple intentions in an online and incremental way.

Intent Detection Keyword Spotting +2

Efficient Keyword Spotting through long-range interactions with Temporal Lambda Networks

16 Apr 2021

To the best of our knowledge, this is the first attempt to examine the Lambda framework within the speech domain and therefore, we unravel further research and development of future speech interfaces based on this architecture.

Keyword Spotting Speech Recognition

End-to-end Keyword Spotting using Neural Architecture Search and Quantization

14 Apr 2021

This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-end keyword spotting (KWS) models in limited resource environments.

Ranked #14 on Keyword Spotting on Google Speech Commands (Google Speech Commands V2 12 metric)

Keyword Spotting Neural Architecture Search +1

The DKU System Description for The Interspeech 2021 Auto-KWS Challenge

11 Apr 2021

This paper introduces the system submitted by the DKU-SMIIP team for the Auto-KWS 2021 Challenge.

Dynamic Time Warping Keyword Spotting +3

A Probabilistic Framework for Lexicon-based Keyword Spotting in Handwritten Text Images

9 Apr 2021

Under this perspective, a probabilistic framework for lexicon-based KWS in text images is presented.

Keyword Spotting

SubSpectral Normalization for Neural Audio Data Processing

25 Mar 2021

In this work, we introduce SubSpectral Normalization (SSN), which splits the input frequency dimension into several groups (sub-bands) and performs a different normalization for each group.

 Ranked #1 on Keyword Spotting on Google Speech Commands (% Test Accuracy metric)

Affine Transformation Keyword Spotting