相关论文: Learning Speech Representation From Contrastive To…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many AC approaches rely on source-target parallel speech data. We propose a…

Training automatic speech recognition (ASR) systems requires large amounts of data in the target language in order to achieve good performance. Whereas large training corpora are readily available for languages like English, there exists a…

Spoken communication plays a central role in clinical workflows. In radiology, for example, most reports are created through dictation. Yet, nearly all medical AI systems rely exclusively on written text. In this work, we address this gap…

We propose Wav2CLIP, a robust audio representation learning method by distilling from Contrastive Language-Image Pre-training (CLIP). We systematically evaluate Wav2CLIP on a variety of audio tasks including classification, retrieval, and…

Self-supervised learning (SSL) approaches, such as contrastive and generative methods, have advanced environmental sound representation learning using unlabeled data. However, how these approaches can complement each other within a unified…

In this paper, we present a novel multi-modal deep neural network architecture that uses speech and text entanglement for learning phonetically sound spoken-word representations. STEPs-RL is trained in a supervised manner to predict the…

Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…

Many speech processing methods based on deep learning require an automatic and differentiable audio metric for the loss function. The DPAM approach of Manocha et al. learns a full-reference metric trained directly on human judgments, and…

Recent advances in video-audio (V-A) understanding and generation have increasingly relied on joint V-A embeddings, which serve as the foundation for tasks such as cross-modal retrieval and generation. While prior methods like CAVP…

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes…

Most existing masked audio modeling (MAM) methods learn audio representations by masking and reconstructing local spectrogram patches. However, the reconstruction loss mainly accounts for the signal-level quality of the reconstructed…

Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpreted as strong…

Soft prompt learning has recently emerged as one of the methods of choice for adapting V&L models to a downstream task using a few training examples. However, current methods significantly overfit the training data, suffering from large…

Expressive speech synthesis, like audiobook synthesis, is still challenging for style representation learning and prediction. Deriving from reference audio or predicting style tags from text requires a huge amount of labeled data, which is…

Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for…

Voice conversion (VC) and text-to-speech (TTS) are two tasks that share a similar objective, generating speech with a target voice. However, they are usually developed independently under vastly different frameworks. In this paper, we…

The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of…

In medical imaging, manual annotations can be expensive to acquire and sometimes infeasible to access, making conventional deep learning-based models difficult to scale. As a result, it would be beneficial if useful representations could be…

Research on multi-modal contrastive learning strategies for audio and text has rapidly gained interest. Contrastively trained Audio-Language Models (ALMs), such as CLAP, which establish a unified representation across audio and language…