Related papers: Approach to Learning Generalized Audio Representat…

Machine learning algorithms, when trained on audio recordings from a limited set of devices, may not generalize well to samples recorded using other devices with different frequency responses. In this work, a relatively straightforward…

In this paper, we propose a simple but powerful unsupervised learning method for speaker recognition, namely Contrastive Equilibrium Learning (CEL), which increases the uncertainty on nuisance factors latent in the embeddings by employing…

Unsupervised single-channel overlapped speech recognition is one of the hardest problems in automatic speech recognition (ASR). Permutation invariant training (PIT) is a state of the art model-based approach, which applies a single neural…

Recent work has begun exploring neural acoustic word embeddings---fixed-dimensional vector representations of arbitrary-length speech segments corresponding to words. Such embeddings are applicable to speech retrieval and recognition tasks,…

This paper evaluates the Audio Spectrogram Transformer (AST) architecture for synthesized speech detection, with focus on generalization across modern voice generation technologies. Using differentiated augmentation strategies, the model…

Audio and speech data are increasingly used in machine learning applications such as speech recognition, speaker identification, and mental health monitoring. However, the passive collection of this data by audio listening devices raises…

Lifelong audio feature extraction involves learning new sound classes incrementally, which is essential for adapting to new data distributions over time. However, optimizing the model only on new data can lead to catastrophic forgetting of…

Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this…

Electroencephalography (EEG) is an essential technique for neuroscience research and brain-computer interface (BCI) applications. Recently, large-scale EEG foundation models have been developed, exhibiting robust generalization capabilities…

Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against…

Labeling and maintaining a commercial sound effects library is a time-consuming task exacerbated by databases that continually grow in size and undergo taxonomy updates. Moreover, sound search and taxonomy creation are complicated by…

Artificial intelligence (AI) is anticipated to emerge as a pivotal enabler for the forthcoming sixth-generation (6G) wireless communication systems. However, current research efforts regarding large AI models for wireless communications…

Prior works have investigated the use of articulatory features as complementary representations for automatic speech recognition (ASR), but their use was largely confined to shallow acoustic models. In this work, we revisit articulatory…

While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- \textit{Internal Covariate Shift}-- the current solution has certain drawbacks. For instance, BN depends on batch…

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtain representations using various sources of information, such…

Generative Adversarial Network (GAN) based vocoders are superior in both inference speed and synthesis quality when reconstructing an audible waveform from an acoustic representation. This study focuses on improving the discriminator for…

Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing…

Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were…

The advent of hyper-scale and general-purpose pre-trained models is shifting the paradigm of building task-specific models for target tasks. In the field of audio research, task-agnostic pre-trained models with high transferability and…

Learning rich visual representations using contrastive self-supervised learning has been extremely successful. However, it is still a major question whether we could use a similar approach to learn superior auditory representations. In this…