Related papers: MixRep: Hidden Representation Mixup for Low-Resour…

Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence,…

RemixIT and Remixed2Remixed are domain adaptation-based speech enhancement (DASE) methods that use a teacher model trained in full supervision to generate pseudo-paired data by remixing the outputs of the teacher model. The student model…

The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we…

Recent advancements in AI have democratized its deployment as a healthcare assistant. While pretrained models from large-scale visual and audio datasets have demonstrably generalized to this task, surprisingly, no studies have explored…

Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recognition (ASR) systems with synthetic audio generated by a TTS…

Mixup is an efficient data augmentation approach that improves the generalization of neural networks by smoothing the decision boundary with mixed data. Recently, dynamic mixup methods have improved previous static policies effectively…

Based on large-scale pre-trained multilingual representations, recent cross-lingual transfer methods have achieved impressive transfer performances. However, the performance of target languages still lags far behind the source language. In…

Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues…

This paper proposes a novel linear prediction coding-based data aug-mentation method for children's low and zero resource dialect ASR. The data augmentation procedure consists of perturbing the formant peaks of the LPC spectrum during LPC…

Despite the rapid advance of automatic speech recognition (ASR) technologies, accurate recognition of cocktail party speech characterised by the interference from overlapping speakers, background noise and room reverberation remains a…

Training speaker-discriminative and robust speaker verification systems without speaker labels is still challenging and worthwhile to explore. In this study, we propose an effective self-supervised learning framework and a novel…

Mixup is a data augmentation method that generates new data points by mixing a pair of input data. While mixup generally improves the prediction performance, it sometimes degrades the performance. In this paper, we first identify the main…

We propose an on-the-fly data augmentation method for automatic speech recognition (ASR) that uses alignment information to generate effective training samples. Our method, called Aligned Data Augmentation (ADA) for ASR, replaces…

In this paper, we explore an improved framework to train a monoaural neural enhancement model for robust speech recognition. The designed training framework extends the existing mixture invariant training criterion to exploit both unpaired…

Considering audio and image data as having quantum nature (data are represented by density matrices), we achieved better results on training architectures such as 3-layer stacked LSTM and HMM by mixing training samples using superposition…

This paper addresses the combination of complementary parallel speech recognition systems to reduce the error rate of speech recognition systems operating in real highly-reverberant environments. First, the testing environment consists of…

Trained on 680,000 hours of massive speech data, Whisper is a multitasking, multilingual speech foundation model demonstrating superior performance in automatic speech recognition, translation, and language identification. However, its…

One of the most important parts of an end-to-end speaker verification system is the speaker embedding generation. In our previous paper, we reported that shortcut connections-based multi-layer aggregation improves the representational power…

Toward high-performance multilingual automatic speech recognition (ASR), various types of linguistic information and model design have demonstrated their effectiveness independently. They include language identity (LID), phoneme…

Multilingual automatic speech recognition (ASR) systems have garnered attention for their potential to extend language coverage globally. While self-supervised learning (SSL) models, like MMS, have demonstrated their effectiveness in…