Adversarial training of Keyword Spotting to Minimize TTS Data Overfitting
The keyword spotting (KWS) problem requires large amounts of real speech training data to achieve high accuracy across diverse populations. Utilizing large amounts of text-to-speech (TTS) synthesized data can reduce the cost and time associated with KWS development. However, TTS data may contain artifacts not present in real speech, which the KWS model can exploit (overfit), leading to degraded accuracy on real speech. To address this issue, we propose applying an adversarial training method to prevent the KWS model from learning TTS-specific features when trained on large amounts of TTS data. Experimental results demonstrate that KWS model accuracy on real speech data can be improved by up to 12% when adversarial loss is used in addition to the original KWS loss. Surprisingly, we also observed that the adversarial setup improves accuracy by up to 8%, even when trained solely on TTS and real negative speech data, without any real positive examples.
Code (0)
등록된 구현이 없습니다.
Tasks
Keyword Spottingtext-to-speechText to SpeechSimilar Papers 제목 키워드 기반
Optimize what matters: Training DNN-HMM Keyword Spotting Model Using End Metric
Deep Neural Network--Hidden Markov Model (DNN-HMM) based methods have been successfully used for many always-on keyword spotting algorithms that detect a wake word to trigger a device. The DNN predicts the state probabil…
DecoderKeyword SpottingGraphemeAug: A Systematic Approach to Synthesized Hard Negative Keyword Spotting Examples
Spoken Keyword Spotting (KWS) is the task of distinguishing between the presence and absence of a keyword in audio. The accuracy of a KWS model hinges on its ability to correctly classify examples close to the keyword an…
Keyword SpottingDisentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting
A keyword spotting (KWS) engine that is continuously running on device is exposed to various speech signals that are usually unseen before. It is a challenging problem to build a small-footprint and high-performing KWS m…
Keyword SpottingSmall-Footprint Keyword SpottingPrototypical Metric Transfer Learning for Continuous Speech Keyword Spotting With Limited Training Data
Continuous Speech Keyword Spotting (CSKS) is the problem of spotting keywords in recorded conversations, when a small number of instances of keywords are available in training data. Unlike the more common Keyword Spottin…
General Classificationimbalanced classificationKeyword SpottingTransfer LearningFew-Shot Keyword Spotting in Any Language
We introduce a few-shot transfer learning method for keyword spotting in any language. Leveraging open speech corpora in nine languages, we automate the extraction of a large multilingual keyword bank and use it to train…
Keyword SpottingTransfer Learning