相关论文: VoxSim: A perceptual voice similarity dataset

We introduce Vox-Profile, a comprehensive benchmark to characterize rich speaker and speech traits using speech foundation models. Unlike existing works that focus on a single dimension of speaker traits, Vox-Profile provides holistic and…

General-purpose audio representations aim to map acoustically variable instances of the same event to nearby points, resolving content identity in a zero-shot setting. Unlike supervised classification benchmarks that measure adaptability…

The success of deep learning in speaker recognition relies heavily on the use of large datasets. However, the data-hungry nature of deep learning methods has already being questioned on account the ethical, privacy, and legal concerns that…

In recent years, an association is established between faces and voices of celebrities leveraging large scale audio-visual information from YouTube. The availability of large scale audio-visual datasets is instrumental in developing speaker…

This paper investigates the use of automatically collected web audio data for the task of spoken language recognition. We generate semi-random search phrases from language-specific Wikipedia data that are then used to retrieve videos from…

This paper proposes VoxStudio, the first unified and end-to-end speech-to-image model that generates expressive images directly from spoken descriptions by jointly aligning linguistic and paralinguistic information. At its core is a speech…

Existing objective evaluation metrics for voice conversion (VC) are not always correlated with human perception. Therefore, training VC models with such criteria may not effectively improve naturalness and similarity of converted speech. In…

Whether it be for results summarization, or the analysis of classifier fusion, some means to compare different classifiers can often provide illuminating insight into their behaviour, (dis)similarity or complementarity. We propose a simple…

Our goal is to collect a large-scale audio-visual dataset with low label noise from videos in the wild using computer vision techniques. The resulting dataset can be used for training and evaluating audio recognition models. We make three…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

Automatic measures of similarity between utterances are invaluable for training speech synthesizers, evaluating machine translation, and assessing learner productions. While there exist measures for semantic similarity and prosodic…

Representations from pre-trained speech foundation models (SFMs) have shown impressive performance in many downstream tasks. However, the potential benefits of incorporating pre-trained SFM representations into speaker voice similarity…

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…

This paper discusses the task of face-based speech synthesis, a kind of personalized speech synthesis where the synthesized voices are constrained to perceptually match with a reference face image. Due to the lack of TTS-quality…

Our native language influences the way we perceive speech sounds, affecting our ability to discriminate non-native sounds. We compare two ideas about the influence of the native language on speech perception: the Perceptual Assimilation…

Recently, researchers set an ambitious goal of conducting speaker recognition in unconstrained conditions where the variations on ambient, channel and emotion could be arbitrary. However, most publicly available datasets are collected under…

The current public datasets for speech recognition (ASR) tend not to focus specifically on the fairness aspect, such as performance across different demographic groups. This paper introduces a novel dataset, Fair-Speech, a publicly released…

Achieving nuanced and accurate emulation of human voice has been a longstanding goal in artificial intelligence. Although significant progress has been made in recent years, the mainstream of speech synthesis models still relies on…

The VoxCeleb Speaker Recognition Challenge (VoxSRC) at Interspeech 2020 offers a challenging evaluation for speaker recognition systems, which includes celebrities playing different parts in movies. The goal of this work is robust speaker…