DeepAI AI Chat
Log In Sign Up

Training Wake Word Detection with Synthesized Speech Data on Confusion Words

by   Yan Jia, et al.

Confusing-words are commonly encountered in real-life keyword spotting applications, which causes severe degradation of performance due to complex spoken terms and various kinds of words that sound similar to the predefined keywords. To enhance the wake word detection system's robustness on such scenarios, we investigate two data augmentation setups for training end-to-end KWS systems. One is involving the synthesized data from a multi-speaker speech synthesis system, and the other augmentation is performed by adding random noise to the acoustic feature. Experimental results show that augmentations help improve the system's robustness. Moreover, by augmenting the training set with the synthetic data generated by the multi-speaker text-to-speech system, we achieve a significant improvement regarding confusing words scenario.


page 2

page 3


Generating Adversarial Samples For Training Wake-up Word Detection Systems Against Confusing Words

Wake-up word detection models are widely used in real life, but suffer f...

Mutli-task Learning with Alignment Loss for Far-field Small-Footprint Keyword Spotting

In this paper, we focus on the task of small-footprint keyword spotting ...

From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint

High-fidelity speech can be synthesized by end-to-end text-to-speech mod...

Enhancement of Pitch Controllability using Timbre-Preserving Pitch Augmentation in FastPitch

The recently developed pitch-controllable text-to-speech (TTS) model, i....

Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network

While standard speaker diarization attempts to answer the question "who ...

Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS

The end-to-end TTS, which can predict speech directly from a given seque...

Investigation of Synthetic Speech Detection Using Frame- and Segment-Specific Importance Weighting

Speaker verification systems are vulnerable to spoofing attacks which pr...