TACos: Learning Temporally Structured Embeddings for Few-Shot Keyword Spotting with Dynamic Time Warping
To segment a signal into blocks to be analyzed, few-shot keyword spotting (KWS) systems often utilize a sliding window of fixed size. Because of the varying lengths of different keywords or their spoken instances, choosing the right window size is a problem: A window should be long enough to contain all necessary information needed to recognize a keyword but a longer window may contain irrelevant information such as multiple words or noise and thus makes it difficult to reliably detect on- and offsets of keywords. We propose TACos, a novel angular margin loss for deriving two-dimensional embeddings that retain temporal properties of the underlying speech signal. In experiments conducted on KWS-DailyTalk, a few-shot KWS dataset presented in this work, using these embeddings as templates for dynamic time warping is shown to outperform using other representations or a sliding window and that using time-reversed segments of the keywords during training improves the performance.
Code (1)
Tasks
Dynamic Time WarpingKeyword SpottingSimilar Papers 제목 키워드 기반
TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining
Learning to associate audio with textual descriptions is valuable for a range of tasks, including pretraining, zero-shot classification, audio retrieval, audio captioning, and text-conditioned audio generation. Existing …
Audio captioningAudio GenerationSentencezero-shot-classification+1TACOS: Task Agnostic COordinator of a multi-drone System
When a single pilot is responsible for managing a multi-drone system, the task may demand varying levels of autonomy, from direct control of individual UAVs, to group-level coordination, to fully autonomous swarm behavio…
Meta-Learning for improving rare word recognition in end-to-end ASR
We propose a new method of generating meaningful embeddings for speech, changes to four commonly used meta learning approaches to enable them to perform keyword spotting in continuous signals and an approach of combining…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Keyword SpottingMeta-Learning+2GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-shot Keyword Spotting
We propose GE2E-KWS -- a generalized end-to-end training and evaluation framework for customized keyword spotting. Specifically, enrollment utterances are separated and grouped by keywords from the training batch and the…
Keyword SpottingTripletADELT: Transpilation Between Deep Learning Frameworks
We propose the Adversarial DEep Learning Transpiler (ADELT), a novel approach to source-to-source transpilation between deep learning frameworks. ADELT uniquely decouples code skeleton transpilation and API keyword mappi…
Deep Learning