Related papers: Adversarial Training For Low-Resource Disfluency C…

Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection…

Semi-supervised learning and domain adaptation techniques have drawn increasing attention in the field of domestic sound event detection thanks to the availability of large amounts of unlabeled data and the relative ease to generate…

In this paper, we propose a Guided Attention (GA) auxiliary training loss, which improves the effectiveness and robustness of automatic speech recognition (ASR) contextual biasing without introducing additional parameters. A common…

High-quality and intelligible speech is essential to text-to-speech (TTS) model training, however, obtaining high-quality data for low-resource languages is challenging and expensive. Applying speech enhancement on Automatic Speech…

Thanks to the rise of self-supervised learning, automatic speech recognition (ASR) systems now achieve near-human performance on a wide variety of datasets. However, they still lack generalization capability and are not robust to domain…

State-of-the-art automatic speech recognition (ASR) models like Whisper, perform poorly on atypical speech, such as that produced by individuals with dysarthria. Past works for atypical speech have mostly investigated fully personalized (or…

Training a robust system, e.g.,Speech to Text (STT), requires large datasets. Variability present in the dataset such as unwanted nuisances and biases are the reason for the need of large datasets to learn general representations. In this…

Recent advancements in deep learning (DL) have posed a significant challenge for automatic speech recognition (ASR). ASR relies on extensive training datasets, including confidential ones, and demands substantial computational and storage…

Stuttering is a neuro-developmental speech impairment characterized by uncontrolled utterances (interjections) and core behaviors (blocks, repetitions, and prolongations), and is caused by the failure of speech sensorimotors. Due to its…

Spelling error correction is the task of identifying and rectifying misspelled words in texts. It is a potential and active research topic in Natural Language Processing because of numerous applications in human language understanding. The…

Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction…

Adversarial examples are maliciously modified inputs created to fool deep neural networks (DNN). The discovery of such inputs presents a major issue to the expansion of DNN-based solutions. Many researchers have already contributed to the…

Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial…

The performance of speech emotion recognition is affected by the differences in data distributions between train (source domain) and test (target domain) sets used to build and evaluate the models. This is a common problem, as multiple…

Speech-based AI models are emerging as powerful tools for detecting depression and the presence of Post-traumatic stress disorder (PTSD), offering a non-invasive and cost-effective way to assess mental health. However, these models often…

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for…

Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for…

Adversarial training has emerged as an effective approach to train robust neural network models that are resistant to adversarial attacks, even in low-label regimes where labeled data is scarce. In this paper, we introduce a novel…

The SOTA in transcription of disfluent and conversational speech has in recent years favored two-stage models, with separate transcription and cleaning stages. We believe that previous attempts at end-to-end disfluency removal have fallen…

Second pass rescoring is a critical component of competitive automatic speech recognition (ASR) systems. Large language models have demonstrated their ability in using pre-trained information for better rescoring of ASR hypothesis.…