SpeechMix - Augmenting Deep Sound Recognition Using Hidden Space Interpolations

By Amit Jindal, Narayanan Elavathur Ranganatha, Aniket Rajiv Didolkar, Arijit Ghosh Chowdhury, Di Jin, Ramit Sawhney, Rajiv Ratn Shah. 2020

19 citations recorded by the source corpus.

This paper presents SpeechMix, a regularization and data augmentation technique for deep sound recognition. Our strategy is to create virtual training samples by interpolating speech samples in hidden space. SpeechMix has the potential to generate an inﬁnite number of new augmented speech samples since the combination of speech samples is continuous. Thus, it allows downstream models to avoid overﬁtting drastically. Unlike other mixing strategies that only work on the input space, we apply our method on the intermediate layers to capture a broader representation of the feature space. Through an extensive quantitative evaluation, we demonstrate the effectiveness of SpeechMix in comparison to standard learning regimes and previously applied mixing strategies. Furthermore, we highlight how different hidden layers contribute to the improvements in classiﬁcation using an ablation study.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Representation & Self-Supervised Learning

In Speech & Audio

In Signal Processing

Citations in the corpus

A Survey of Data Augmentation Approaches for NLP (2021, background): “, 2018b) × × tok Input × EMIX (Jindal et al., 2019) × × - Emb/Hidden 3 MIXTEXT (Chen et al.”