相关论文: Zimtohrli: An Efficient Psychoacoustic Audio Simil…

We introduce a new automatic evaluation method for speaker similarity assessment, that is consistent with human perceptual scores. Modern neural text-to-speech models require a vast amount of clean training data, which is why many solutions…

Spatial audio enhances immersion in applications such as virtual reality, augmented reality, gaming, and cinema by creating a three-dimensional auditory experience. Ensuring the spatial fidelity of binaural audio is crucial, given that…

Voice imitation aims to transform source speech to match a reference speaker's timbre and speaking style while preserving linguistic content. A straightforward approach is to train on triplets of (source, reference, target), where source…

In this study, we investigate the feasibility of utilizing state-of-the-art image perceptual metrics for evaluating audio signals by representing them as spectrograms. The encouraging outcome of the proposed approach is based on the…

Subjective evaluations are critical for assessing the perceptual realism of sounds in audio-synthesis driven technologies like augmented and virtual reality. However, they are challenging to set up, fatiguing for users, and expensive. In…

Psychoacoustical so-called "timbre spaces" map perceptual similarity ratings of instrument sounds onto low-dimensional embeddings via multidimensional scaling, but suffer from scalability issues and are incapable of generalization. Recent…

State-of-the-art deep learning based stereo matching approaches treat disparity estimation as a regression problem, where loss function is directly defined on true disparities and their estimated ones. However, disparity is just a byproduct…

This paper presents NOMAD (Non-Matching Audio Distance), a differentiable perceptual similarity metric that measures the distance of a degraded signal against non-matching references. The proposed method is based on learning deep feature…

Many audio processing tasks require perceptual assessment. The ``gold standard`` of obtaining human judgments is time-consuming, expensive, and cannot be used as an optimization criterion. On the other hand, automated metrics are efficient…

Biomimicry is a powerful science that takes advantage of nature's remarkable ability to devise innovative solutions to challenging problems. In this work, we use asymptotic methods to develop the mathematical foundations for the exchange of…

Although perceptual (dis)similarity between sensory stimuli seems akin to distance, measuring the Euclidean distance between vector representations of auditory stimuli is a poor estimator of subjective dissimilarity. In hearing, nonlinear…

Eurich et al. (2024) recently introduced the computationally efficient monaural and binaural audio quality model (eMoBi-Q). This model integrates both monaural and binaural auditory features and has been validated across six audio datasets…

Many audio processing tasks require perceptual assessment. However, the time and expense of obtaining ``gold standard'' human judgments limit the availability of such data. Most applications incorporate full reference or other…

In this paper, we propose a novel information theoretic model to interpret the entire "transmission chain" comprising stimulus generation, brain processing by the human subject, and the electroencephalograph (EEG) response measurements as a…

Speech quality assessment typically requires evaluating audio from multiple aspects, such as mean opinion score (MOS) and speaker similarity (SIM) \etc., which can be challenging to cover using one small model designed for a single task. In…

While audio quality is a key performance metric for various audio processing tasks, including generative modeling, its objective measurement remains a challenge. Audio-Language Models (ALMs) are pre-trained on audio-text pairs that may…

In the development of spatial audio technologies, reliable and shared methods for evaluating audio quality are essential. Listening tests are currently the standard but remain costly in terms of time and resources. Several models predicting…

Audio quality assessment is critical for assessing the perceptual realism of sounds. However, the time and expense of obtaining ''gold standard'' human judgments limit the availability of such data. For AR&VR, good perceived sound quality…

Standard evaluation metrics such as the Inception score and Fr\'echet Audio Distance provide a general audio quality distance metric between the synthesized audio and reference clean audio. However, the sensitivity of these metrics to…

In this paper, we propose the coarse-to-fine optimization for the task of speech enhancement. Cosine similarity loss [1] has proven to be an effective metric to measure similarity of speech signals. However, due to the large variance of the…