Related papers: M2H-GAN: A GAN-based Mapping from Machine to Human…
Deep neural networks (DNN) are quickly becoming the de facto standard modeling method for many natural language generation (NLG) tasks. In order for such models to truly be useful, they must be capable of correctly generating utterances for…
In the traditional cascading architecture for spoken language understanding (SLU), it has been observed that automatic speech recognition errors could be detrimental to the performance of natural language understanding. End-to-end (E2E) SLU…
Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…
In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted…
Producing a large annotated speech corpus for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced, but collecting a relatively big unlabeled data set for such languages is more…
Due to the subjective nature of current clinical evaluation, the need for automatic severity evaluation in dysarthric speech has emerged. DNN models outperform ML models but lack user-friendly explainability. ML models offer explainable…
Deep Neural Networks (DNN) have been successful in en- hancing noisy speech signals. Enhancement is achieved by learning a nonlinear mapping function from the features of the corrupted speech signal to that of the reference clean speech…
A deep learning approach has been proposed recently to derive speaker identifies (d-vector) by a deep neural network (DNN). This approach has been applied to text-dependent speaker recognition tasks and shows reasonable performance gains…
This paper describes a general, scalable, end-to-end framework that uses the generative adversarial network (GAN) objective to enable robust speech recognition. Encoders trained with the proposed approach enjoy improved invariance by…
Inverse text normalization (ITN) is crucial for converting spoken-form into written-form, especially in the context of automatic speech recognition (ASR). While most downstream tasks of ASR rely on written-form, ASR systems often output…
In most safety-critical domains the need for traceability is prescribed by certifying bodies. Trace links are generally created among requirements, design, source code, test cases and other artifacts, however, creating such links manually…
Neural machine translation models have shown to achieve high quality when trained and fed with well structured and punctuated input texts. Unfortunately, the latter condition is not met in spoken language translation, where the input is…
Modern topic identification (topic ID) systems for speech use automatic speech recognition (ASR) to produce speech transcripts, and perform supervised classification on such ASR outputs. However, under resource-limited conditions, the…
Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large quantities of…
Spoken language understanding (SLU) systems in conversational AI agents often experience errors in the form of misrecognitions by automatic speech recognition (ASR) or semantic gaps in natural language understanding (NLU). These errors…
In safety-critical systems (e.g., autonomous vehicles and robots), Deep Neural Networks (DNNs) are becoming a key component for computer vision tasks, particularly semantic segmentation. Further, since the DNN behavior cannot be assessed…
Research on speech processing has traditionally considered the task of designing hand-engineered acoustic features (feature engineering) as a separate distinct problem from the task of designing efficient machine learning (ML) models to…
Recent studies have shown that deep neural networks (DNNs) perform significantly better than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech recognition tasks. In this paper, we argue that the improved…
Current speech-based LLMs are predominantly trained on extensive ASR and TTS datasets, excelling in tasks related to these domains. However, their ability to handle direct speech-to-speech conversations remains notably constrained. These…
Speech enhancement aims to obtain speech signals with high intelligibility and quality from noisy speech. Recent work has demonstrated the excellent performance of time-domain deep learning methods, such as Conv-TasNet. However, these…