Ctc-aligned Audio-text Embedding For Streaming Open-vocabulary Keyword Spotting

Abstract

This paper introduces a novel approach for streaming openvocabulary keyword spotting (KWS) with text-based keyword enrollment. For every input frame, the proposed method finds the optimal alignment ending at the frame using connectionist temporal classification (CTC) and aggregates the frame-level acoustic embedding (AE) to obtain higher-level (i.e., character, word, or phrase) AE that aligns with the text embedding (TE) of the target keyword text. After that, we calculate the similarity of the aggregated AE and the TE. To the best of our knowledge, this is the first attempt to dynamically align the audio and the keyword text on-the-fly to attain the joint audio-text embedding for KWS. Despite operating in a streaming fashion, our approach achieves competitive performance on the LibriPhrase dataset compared to the non-streaming methods with a mere 155K model parameters and a decoding algorithm with time complexity O(U), where U is the length of the target keyword at inference time.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyjin2024ctc

Related papers

• Streaming Keyword Spotting Boosted By Cross-layer Discrimination Consistency (2024)6.34
• Online Continual Learning In Keyword Spotting For Low-resource Devices Via Pooling High-order Temporal Statistics (2023)7.50
• GE2E-KWS: Generalized End-to-end Training And Evaluation For Zero-shot Keyword Spotting (2024)2.26
• Exploring Sequence-to-sequence Transformer-transducer Models For Keyword Spotting (2022)5.24
• End-to-end Streaming Keyword Spotting (2018)12.10
• Streaming Small-footprint Keyword Spotting Using Sequence-to-sequence Models (2017)12.40
• Small-footprint Keyword Spotting Using Deep Neural Network And Connectionist Temporal Classifier (2017)0.00
• Llm-synth4kws: Scalable Automatic Generation And Synthesis Of Confusable Data For Custom Keyword Spotting (2025)2.26