A neural attention model for speech command recognition

2018/08/27 by Douglas Coimbra de Andrade, de Andrade, Douglas Coimbra, S. Leo +5 · 5 citations
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #Speech and dialogue systems #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1808.08929

openalex publication_date 2018/08/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model establishes a new state-of-the-art accuracy of 94.1% on Google Speech Commands dataset V1 and 94.5% on V2 (for the 20-commands recognition task), while still keeping a small footprint of only 202K trainable parameters. Results are compared with previous convolutional implementations on 5 different tasks (20 commands recognition (V1 and V2), 12 commands recognition (V1), 35 word recognition (V1) and left-right (V1)). We show detailed performance results and demonstrate that the proposed attention mechanism not only improves performance but also allows inspecting what regions of the audio were taken into consideration by the network when outputting a given category.

Citations

• Neural Machine Translation by Jointly Learning to Align and Translate
• Hello Edge: Keyword Spotting on Microcontrollers

Cited by

• Parallel Delayed Memory Units for Enhanced Temporal Modeling in Biomedical and Bioacoustic Signal Analysis
• A Streaming End-to-End Framework For Spoken Language Understanding
• Speech Command Recognition Using LogNNet Reservoir Computing for Embedded Systems
• Interpretable Super-Resolution via a Learned Time-Series Representation
• IC Neuron: An Efficient Unit to Construct Neural Networks

Related

• Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognition
• An Empirical Analysis of Deep Audio-Visual Models for Speech Recognition
• Multi-layer Attention Mechanism for Speech Keyword Recognition
• Frequency and temporal convolutional attention for text-independent\n speaker recognition
• Attention-Based Models for Speech Recognition