Related papers: Wav2vec-C: A Self-supervised Model for Speech Repr…

In this study, we investigate self-supervised representation learning for speaker verification (SV). First, we examine a simple contrastive learning approach (SimCLR) with a momentum contrastive (MoCo) learning framework, where the MoCo…

Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply…

The popular frameworks for self-supervised learning of speech representations have largely focused on frame-level masked prediction of speech regions. While this has shown promising downstream task performance for speech recognition and…

Conventional spoofing detection systems have heavily relied on the use of handcrafted features derived from speech data. However, a notable shift has recently emerged towards the direct utilization of raw speech waveforms, as demonstrated…

We present RAVEn, a self-supervised multi-modal approach to jointly learn visual and auditory speech representations. Our pre-training objective involves encoding masked inputs, and then predicting contextualised targets generated by…

State-of-the-art Variational Auto-Encoders (VAEs) for learning disentangled latent representations give impressive results in discovering features like pitch, pause duration, and accent in speech data, leading to highly controllable…

An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoencoders to learn…

A singing voice conversion model converts a song in the voice of an arbitrary source singer to the voice of a target singer. Recently, methods that leverage self-supervised audio representations such as HuBERT and Wav2Vec 2.0 have helped…

In this paper, we first extend the recent Masked Auto-Encoder (MAE) model from a single modality to audio-visual multi-modalities. Subsequently, we propose the Contrastive Audio-Visual Masked Auto-Encoder (CAV-MAE) by combining contrastive…

We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that…

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…

Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this paper, we introduce a novel semi-supervised text-to-speech synthesis model that learns from both paired…

Self-supervised learned (SSL) models such as Wav2vec and HuBERT yield state-of-the-art results on speech-related tasks. Given the effectiveness of such models, it is advantageous to use them in conventional ASR systems. While some…

ASR systems designed for native English (L1) usually underperform on non-native English (L2). To address this performance gap, \textbf{(i)} we extend our previous work to investigate fine-tuning of a pre-trained wav2vec 2.0 model…

We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality…

This paper is a study of performance-efficiency trade-offs in pre-trained models for automatic speech recognition (ASR). We focus on wav2vec 2.0, and formalize several architecture designs that influence both the model performance and its…

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…

Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio…

Wav2vec 2.0 is a state-of-the-art speech recognition model which maps speech audio waveforms into latent representations. The largest version of wav2vec 2.0 contains 317 million parameters. Hence, the inference latency of wav2vec 2.0 will…

Visual Speech Recognition (VSR) differs from the common perception tasks as it requires deeper reasoning over the video sequence, even by human experts. Despite the recent advances in VSR, current approaches rely on labeled data to fully…