相关论文: Speech Quality Assessment through MOS using Non-Ma…

The evaluation of synthetic and processed speech has long been a cornerstone of audio engineering and speech science. Although subjective listening tests remain the gold standard for assessing perceptual quality and intelligibility, their…

This technical report describes our system that is submitted to the Deep Noise Suppression Challenge and presents the results for the non-real-time track. To refine the estimation results stage by stage, we utilize recursive learning, a…

We describe Microsoft's conversational speech recognition system, in which we combine recent developments in neural-network-based acoustic and language modeling to advance the state of the art on the Switchboard recognition task. Inspired…

In this paper, we present a full-reference speech quality prediction model with a deep learning approach. The model determines a feature representation of the reference and the degraded signal through a siamese recurrent convolutional…

Traditionally, research in automated speech recognition has focused on local-first encoding of audio representations to predict the spoken phonemes in an utterance. Unfortunately, approaches relying on such hyper-local information tend to…

For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions. In traditional hidden Markov model-based automatic speech recognition (ASR) systems, confidence…

No-Reference Image Quality Assessment (NR-IQA) remains a challenging task due to the diversity of distortions and the lack of large annotated datasets. Many studies have attempted to tackle these challenges by developing more accurate…

Utilizing a human-perception-related objective function to train a speech enhancement model has become a popular topic recently. The main reason is that the conventional mean squared error (MSE) loss cannot represent auditory perception…

While human evaluation is the most reliable metric for evaluating speech generation systems, it is generally costly and time-consuming. Previous studies on automatic speech quality assessment address the problem by predicting human…

Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely…

Understanding semantic information is an essential step in knowing what is being learned in both full-reference (FR) and no-reference (NR) image quality assessment (IQA) methods. However, especially for many severely distorted images, even…

Self-supervised language and audio models effectively predict brain responses to speech. However, traditional prediction models rely on linear mappings from unimodal features, despite the complex integration of auditory signals with…

Image Quality Assessment algorithms predict a quality score for a pristine or distorted input image, such that it correlates with human opinion. Traditional methods required a non-distorted "reference" version of the input image to compare…

Machine learning techniques are an active area of research for speech enhancement for hearing aids, with one particular focus on improving the intelligibility of a noisy speech signal. Recent work has shown that feature encodings from…

Improving subjective sound quality of enhanced signals is one of the most important missions in speech enhancement. For evaluating the subjective quality, several methods related to perceptually-motivated objective sound quality assessment…

We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…

Speech enhancement techniques improve the quality or the intelligibility of an audio signal by removing unwanted noise. It is used as preprocessing in numerous applications such as speech recognition, hearing aids, broadcasting and…

The quality of meeting summaries generated by natural language generation (NLG) systems is hard to measure automatically. Established metrics such as ROUGE and BERTScore have a relatively low correlation with human judgments and fail to…

No-Reference Image Quality Assessment for distorted images has always been a challenging problem due to image content variance and distortion diversity. Previous IQA models mostly encode explicit single-quality features of synthetic images…

In a subjective experiment to evaluate the perceptual audiovisual quality of multimedia and television services, raw opinion scores collected from test subjects are often noisy and unreliable. To produce the final mean opinion scores (MOS),…