Related papers: PhasePerturbation: Speech Data Augmentation via Ph…

In recent years, the performance of automatic speech recognition (ASR) systems has made considerable progress. Unfortunately, for people with speech impairments, such as people treated for oral cancer (OC), ASR performance is still lagging…

Data augmentation is vital to the generalization ability and robustness of deep neural networks (DNNs) models. Existing augmentation methods for speaker verification manipulate the raw signal, which are time-consuming and the augmented…

While Wav2Vec 2.0 has been proposed for speech recognition (ASR), it can also be used for speech emotion recognition (SER); its performance can be significantly improved using different fine-tuning strategies. Two baseline methods, vanilla…

Automatic speech recognition (ASR) should serve every speaker, not only the majority ``standard'' speakers of a language. In order to build inclusive ASR, mitigating the bias against speaker groups who speak in a ``non-standard'' or…

This paper proposes APSS, a novel neural speech separation model with parallel amplitude and phase spectrum estimation. Unlike most existing speech separation methods, the APSS distinguishes itself by explicitly estimating the phase…

In automatic speech recognition, often little training data is available for specific challenging tasks, but training of state-of-the-art automatic speech recognition systems requires large amounts of annotated speech. To address this…

This study investigates the impact of integrating a dataset of disordered speech recordings ($\sim$1,000 hours) into the fine-tuning of a near state-of-the-art ASR baseline system. Contrary to what one might expect, despite the data being…

We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation…

In this paper, we aim to unveil the impact of data augmentation in audio-language multi-modal learning, which has not been explored despite its importance. We explore various augmentation methods at not only train-time but also test-time…

Recently, end-to-end (E2E) automatic speech recognition (ASR) models have made great strides and exhibit excellent performance in general speech recognition. However, there remain several challenging scenarios that E2E models are not…

Data augmentation techniques are widely used in low-resource automatic morphological inflection to overcome data sparsity. However, the full implications of these techniques remain poorly understood. In this study, we aim to shed light on…

Automatic speech recognition (ASR) for conversational code-switching speech remains challenging due to the scarcity of realistic, high-quality labeled speech data. This paper explores multilingual text-to-speech (TTS) models as an effective…

Speech emotion recognition (SER) has drawn increasing attention for its applications in human-machine interaction. However, existing SER methods ignore the information gap between the pre-training speech recognition task and the downstream…

Automatic speech recognition (ASR) systems are known to be sensitive to the sociolinguistic variability of speech data, in which gender plays a crucial role. This can result in disparities in recognition accuracy between male and female…

End-to-end (E2E) multi-channel ASR systems show state-of-the-art performance in far-field ASR tasks by joint training of a multi-channel front-end along with the ASR model. The main limitation of such systems is that they are usually…

Automatic speech recognition (ASR) systems for young children are needed due to the importance of age-appropriate educational technology. Because of the lack of publicly available young child speech data, feature extraction strategies such…

The recent advances in voice conversion (VC) and text-to-speech (TTS) make it possible to produce natural sounding speech that poses threat to automatic speaker verification (ASV) systems. To this end, research on spoofing countermeasures…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

The optimization of a wavelet-based algorithm to improve speech intelligibility along with the full data set and results are reported. The discrete-time speech signal is split into frequency sub-bands via a multi-level discrete wavelet…

This paper proposes a speech enhancement method which exploits the high potential of residual connections in a Wide Residual Network architecture. This is supported on single dimensional convolutions computed alongside the time domain,…