相关论文: Universal Preference-Score-based Pairwise Speech Q…

Persona-based dialogue generation is an important milestone towards building conversational artificial intelligence. Despite the ever-improving capabilities of large language models (LLMs), effectively integrating persona fidelity in…

Speech enhancement is crucial for ubiquitous human-computer interaction. Recently, ultrasound-based acoustic sensing has emerged as an attractive choice for speech enhancement because of its superior ubiquity and performance. However, due…

Diffusion probabilistic models have demonstrated an outstanding capability to model natural images and raw audio waveforms through a paired diffusion and reverse processes. The unique property of the reverse process (namely, eliminating…

As large language models (LLMs) are increasingly used as evaluators for natural language generation tasks, ensuring unbiased assessments is essential. However, LLM evaluators often display biased preferences, such as favoring verbosity and…

The ground truth used for training image, video, or speech quality prediction models is based on the Mean Opinion Scores (MOS) obtained from subjective experiments. Usually, it is necessary to conduct multiple experiments, mostly with…

In online conferencing applications, estimating the perceived quality of an audio signal is crucial to ensure high quality of experience for the end user. The most reliable way to assess the quality of a speech signal is through human…

Universal speech enhancement (USE) aims to restore speech signals from diverse distortions across multiple sampling rates. We propose UniPASE, an extension of the low-hallucination PASE framework tailored for USE. At its core is…

Unsupervised feature selection (UFS) is widely applied in machine learning and pattern recognition. However, most of the existing methods only consider a single sparsity, which makes it difficult to select valuable and discriminative…

Recent advances in preference optimization have demonstrated significant potential for improving mathematical reasoning capabilities in large language models (LLMs). While current approaches leverage high-quality pairwise preference data…

As language models (LMs) become more capable, it is increasingly important to align them with human preferences. However, the dominant paradigm for training Preference Models (PMs) for that purpose suffers from fundamental limitations, such…

A preference-based subjective evaluation is a key method for evaluating generative media reliably. However, its huge combinations of pairs prohibit it from being applied to large-scale evaluation using crowdsourcing. To address this issue,…

Automatic Mean Opinion Score (MOS) prediction is employed to evaluate the quality of synthetic speech. This study extends the application of predicted MOS to the task of Fake Audio Detection (FAD), as we expect that MOS can be used to…

We propose a Perceiver-based sequence classifier to detect abnormalities in speech reflective of several neurological disorders. We combine this classifier with a Universal Speech Model (USM) that is trained (unsupervised) on 12 million…

Sentiment analysis is a pivotal task in the domain of natural language processing. It encompasses both text-level sentiment polarity classification and word-level Part of Speech(POS) sentiment polarity determination. Such analysis…

Speech quality assessment (SQA) aims to predict the perceived quality of speech signals under a wide range of distortions. It is inherently connected to speech enhancement (SE), which seeks to improve speech quality by removing unwanted…

Human preference plays a significant role in measuring large language models and guiding them to align with human values. Unfortunately, current comparing-based evaluation (CBE) methods typically focus on a single optimization objective,…

Universal speech enhancement aims at handling inputs with various speech distortions and recording conditions. In this work, we propose a novel hybrid architecture that synergizes the signal fidelity of discriminative modeling with the…

Recent work suggests that large language models enhanced with retrieval-augmented generation are easily influenced by the order, in which the retrieved documents are presented to the model when solving tasks such as question answering (QA).…

Automatic speech quality assessment is an important, transversal task whose progress is hampered by the scarcity of human annotations, poor generalization to unseen recording conditions, and a lack of flexibility of existing approaches. In…

Modern speech quality prediction models are trained on audio data resampled to a specific sampling rate. When faced with higher-rate audio at test time, these models can produce biased scores. We introduce HighRateMOS, the first…