相关论文: Adversarial Training For Low-Resource Disfluency C…

In modern interactive speech-based systems, speech is consumed and transcribed incrementally prior to having disfluencies removed. This post-processing step is crucial for producing clean transcripts and high performance on downstream tasks…

We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the inter-talker feature variability while maximizing its senone discriminability so as to enhance the performance of a deep neural network (DNN) based…

Automated Speech Recognition (ASR) is an interdisciplinary application of computer science and linguistics that enable us to derive the transcription from the uttered speech waveform. It finds several applications in Military like…

It is an effective way that improves the performance of the existing Automatic Speech Recognition (ASR) systems by retraining with more and more new training data in the target domain. Recently, Deep Neural Network (DNN) has become a…

While a streaming voice assistant system has been used in many applications, this system typically focuses on unnatural, one-shot interactions assuming input from a single voice query without hesitation or disfluency. However, a common…

Speech applications dealing with conversations require not only recognizing the spoken words but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate systems,…

Recently, more and more personalized speech enhancement systems (PSE) with excellent performance have been proposed. However, two critical issues still limit the performance and generalization ability of the model: 1) Acoustic environment…

We propose a reinforcement learning (RL)-based system that would automatically prescribe a hypothetical patient medication that may help the patient with their mental health-related speech disfluency, and adjust the medication and the…

Self-supervised learned (SSL) speech pre-trained models perform well across various speech processing tasks. Distilled versions of SSL models have been developed to match the needs of on-device speech applications. Though having similar…

It is challenging to improve automatic speech recognition (ASR) performance in noisy conditions with a single-channel speech enhancement (SE) front-end. This is generally attributed to the processing distortions caused by the nonlinear…

Besides the well-known classification task, these days neural networks are frequently being applied to generate or transform data, such as images and audio signals. In such tasks, the conventional loss functions like the mean squared error…

Effective communication in Air Traffic Control (ATC) is critical to maintaining aviation safety, yet the challenges posed by accented English remain largely unaddressed in Automatic Speech Recognition (ASR) systems. Existing models struggle…

Stuttering is a speech disorder where the natural flow of speech is interrupted by blocks, repetitions or prolongations of syllables, words and phrases. The majority of existing automatic speech recognition (ASR) interfaces perform poorly…

In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) systems. To alleviate this issue, the commonest way is to use a…

Off-the-shelf pre-trained Automatic Speech Recognition (ASR) systems are an increasingly viable service for companies of any size building speech-based products. While these ASR systems are trained on large amounts of data, domain mismatch…

The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…

Recently self-supervised learning has emerged as an effective approach to improve the performance of automatic speech recognition (ASR). Under such a framework, the neural network is usually pre-trained with massive unlabeled data and then…

Specially adapted speech recognition models are necessary to handle stuttered speech. For these to be used in a targeted manner, stuttered speech must be reliably detected. Recent works have treated stuttering as a multi-class…

Adversarial training is one of the best-performing methods in improving the robustness of deep language models. However, robust models come at the cost of high time consumption, as they require multi-step gradient ascents or word…

Text-to-audio systems, while increasingly performant, are slow at inference time, thus making their latency unpractical for many creative applications. We present Adversarial Relativistic-Contrastive (ARC) post-training, the first…