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

The use of spatial information with multiple microphones can improve far-field automatic speech recognition (ASR) accuracy. However, conventional microphone array techniques degrade speech enhancement performance when there is an array…

Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervised setting. By noticing the mixed images that share the same…

Improving end-to-end speech recognition by incorporating external text data has been a longstanding research topic. There has been a recent focus on training E2E ASR models that get the performance benefits of external text data without…

Aligned audio corpora are fundamental to NLP technologies such as ASR and speech translation, yet they remain scarce for underrepresented languages, hindering their technological integration. This paper introduces a methodology for…

The Mixture of Experts (MoE) models are emerging as the latest paradigm for Large Language Models (LLMs). However, due to memory constraints, MoE models with billions or even trillions of parameters can only be deployed in multi-GPU or even…

Network calibration aims to accurately estimate the level of confidences, which is particularly important for employing deep neural networks in real-world systems. Recent approaches leverage mixup to calibrate the network's predictions…

This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is…

In this paper, we propose a weakly supervised multilingual representation learning framework, called cross-lingual self-training (XLST). XLST is able to utilize a small amount of annotated data from high-resource languages to improve the…

This paper presents a novel data augmentation technique for text-to-speech (TTS), that allows to generate new (text, audio) training examples without requiring any additional data. Our goal is to increase diversity of text conditionings…

With the rapid development of deep learning, automatic modulation recognition (AMR), as an important task in cognitive radio, has gradually transformed from traditional feature extraction and classification to automatic classification by…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

Audio-visual speech recognition (AVSR) has gained remarkable success for ameliorating the noise-robustness of speech recognition. Mainstream methods focus on fusing audio and visual inputs to obtain modality-invariant representations.…

Self-supervised learning of speech representations has achieved impressive results in improving automatic speech recognition (ASR). In this paper, we show that data selection is important for self-supervised learning. We propose a simple…

While many speakers of low-resource languages regularly code-switch between their languages and other regional languages or English, datasets of codeswitched speech are too small to train bespoke acoustic models from scratch or do language…

Using neural network based acoustic frontends for improving robustness of streaming automatic speech recognition (ASR) systems is challenging because of the causality constraints and the resulting distortion that the frontend processing…

Prior works have investigated the use of articulatory features as complementary representations for automatic speech recognition (ASR), but their use was largely confined to shallow acoustic models. In this work, we revisit articulatory…

This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates. Considering the narrowband spectrogram as a sub-image of the wideband spectrogram, we tackle the joint modeling problem…

Mixup and its variants form a popular class of data augmentation techniques.Using a random sample pair, it generates a new sample by linear interpolation of the inputs and labels. However, generating only one single interpolation may limit…

This paper presents our system for the MISP-Meeting Challenge Track 2. The primary difficulty lies in the dataset, which contains strong background noise, reverberation, overlapping speech, and diverse meeting topics. To address these…

Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…