相关论文: Selecting N-lowest scores for training MOS predict…

In this research, we propose an architectural solution to implement the voice over IP (VoIP) service in campus environment network. Voice over IP (VoIP) technology has become a discussion issue for this time being. Today, the deployment of…

This work adapts two recent architectures of generative models and evaluates their effectiveness for the conversion of whispered speech to normal speech. We incorporate the normal target speech into the training criterion of…

State-of-the-art sequence-to-sequence acoustic networks, that convert a phonetic sequence to a sequence of spectral features with no explicit prosody prediction, generate speech with close to natural quality, when cascaded with neural…

Traditionally, the quality of acoustic echo cancellers is evaluated using intrusive speech quality assessment measures such as ERLE \cite{g168} and PESQ \cite{p862}, or by carrying out subjective laboratory tests. Unfortunately, the former…

Modern speaker recognition system relies on abundant and balanced datasets for classification training. However, diverse defective datasets, such as partially-labelled, small-scale, and imbalanced datasets, are common in real-world…

Neural audio codecs have recently gained popularity because they can represent audio signals with high fidelity at very low bitrates, making it feasible to use language modeling approaches for audio generation and understanding. Residual…

Recent learning-based video quality assessment (VQA) algorithms are expensive to implement due to the cost of data collection of human quality opinions, and are less robust across various scenarios due to the biases of these opinions. This…

Recent speech enhancement (SE) models increasingly leverage self-supervised learning (SSL) representations for their rich semantic information. Typically, intermediate features are aggregated into a single representation via a lightweight…

Spoken question answering (SQA) requires fine-grained understanding of both spoken documents and questions for the optimal answer prediction. In this paper, we propose novel training schemes for spoken question answering with a…

For the quantification of QoE, subjects often provide individual rating scores on certain rating scales which are then aggregated into Mean Opinion Scores (MOS). From the observed sample data, the expected value is to be estimated. While…

Objective speech-quality metrics are widely used to assess codec performance. However, for neural codecs, it is often unclear which metrics provide reliable quality estimates. To address this, we evaluated 45 objective metrics by…

Deep-learning based techniques have contributed to the remarkable progress in the field of automatic image quality assessment (IQA). Existing IQA methods are designed to measure the quality of an image in terms of Mean Opinion Score (MOS)…

This study investigates the evaluation of multimedia quality models, focusing on the inherent uncertainties in subjective Mean Opinion Score (MOS) ratings due to factors like rater inconsistency and bias. Traditional statistical measures…

This paper proposes an approach to detect emotion from human speech employing majority voting technique over several machine learning techniques. The contribution of this work is in two folds: firstly it selects those features of speech…

Speech self-supervised pre-training can effectively improve the performance of downstream tasks. However, previous self-supervised learning (SSL) methods for speech, such as HuBERT and BEST-RQ, focus on utilizing non-causal encoders with…

The performances of the automatic speaker verification (ASV) systems degrade due to the reduction in the amount of speech used for enrollment and verification. Combining multiple systems based on different features and classifiers…

While subjective assessments have been the gold standard for evaluating speech generation, there is a growing need for objective metrics that are highly correlated with human subjective judgments due to their cost efficiency. This paper…

Traditional in the wild image quality assessment (IQA) models are generally trained with the quality labels of mean opinion score (MOS), while missing the rich subjective quality information contained in the quality ratings, for example,…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

The estimation of speech intelligibility is still far from being a solved problem. Especially one aspect is problematic: most of the standard models require a clean reference signal in order to estimate intelligibility. This is an issue of…