相关论文: voc2vec: A Foundation Model for Non-Verbal Vocaliz…

We propose emotion2vec, a universal speech emotion representation model. emotion2vec is pre-trained on open-source unlabeled emotion data through self-supervised online distillation, combining utterance-level loss and frame-level loss…

Recognizing human non-speech vocalizations is an important task and has broad applications such as automatic sound transcription and health condition monitoring. However, existing datasets have a relatively small number of vocal sound…

Understanding how speech foundation models capture non-verbal cues is crucial for improving their interpretability and adaptability across diverse tasks. In our work, we analyze several prominent models such as Whisper, Seamless, Wav2Vec,…

The objective of this paper is speaker recognition under noisy and unconstrained conditions. We make two key contributions. First, we introduce a very large-scale audio-visual speaker recognition dataset collected from open-source media.…

Both speech and sensor time series data encode information in both the time- and frequency- domains, like spectral powers and waveform shapelets. We show that speech foundation models learn representations that generalize beyond the speech…

The studies of predicting affective states from human voices have relied heavily on speech. This study, indeed, explores the recognition of humans' affective state from their vocal burst, a short non-verbal vocalization. Borrowing the idea…

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…

Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning. It follows a two-stage training process of pre-training and fine-tuning, and performs well in speech recognition tasks especially ultra-low…

Self-supervised learning methods such as wav2vec 2.0 have shown promising results in learning speech representations from unlabelled and untranscribed speech data that are useful for speech recognition. Since these representations are…

This paper introduces FastVC, an end-to-end model for fast Voice Conversion (VC). The proposed model can convert speech of arbitrary length from multiple source speakers to multiple target speakers. FastVC is based on a conditional…

We explore unsupervised pre-training for speech recognition by learning representations of raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting representations are then used to improve acoustic model…

This paper introduces VoxSim, a dataset of perceptual voice similarity ratings. Recent efforts to automate the assessment of speech synthesis technologies have primarily focused on predicting mean opinion score of naturalness, leaving…

Non-Verbal Vocalisations (NVVs) are short `non-word' utterances without proper linguistic (semantic) meaning but conveying connotations -- be this emotions/affects or other paralinguistic information. We start this contribution with a…

In this paper, we provide a large audio-visual speaker recognition dataset, VoxBlink2, which includes approximately 10M utterances with videos from 110K+ speakers in the wild. This dataset represents a significant expansion over the…

The assessment of children at risk of autism typically involves a clinician observing, taking notes, and rating children's behaviors. A machine learning model that can label adult and child audio may largely save labor in coding children's…

Transfer learning using latent representations from pre-trained speech models achieves outstanding performance in tasks where labeled data is scarce. However, their applicability to non-speech data and the specific acoustic properties…

Speech technology systems struggle with many downstream tasks for child speech due to small training corpora and the difficulties that child speech pose. We apply a novel dataset, SpeechMaturity, to state-of-the-art transformer models to…

This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition. We study the effectiveness of the pre-trained weights on the speaker recognition task, and how to pool the wav2vec2 output sequence…

Using representations provided by a large pre-trained model has become the primary strategy for achieving state-of-the-art results in a wide range of tasks. A recently proposed large pre-trained model, wav2vec 2.0, was seminal for several…

We present ChildVox, a novel benchmark for characterizing the diverse acoustic signals through which children communicate. Specifically, ChildVox follows the full developmental trajectory from birth through school age, covering…