Related papers: Small energy masking for improved neural network t…

Training large foundation models using self-supervised objectives on unlabeled data, followed by fine-tuning on downstream tasks, has emerged as a standard procedure. Unfortunately, the efficacy of this approach is often constrained by both…

The optimization of a wavelet-based algorithm to improve speech intelligibility along with the full data set and results are reported. The discrete-time speech signal is split into frequency sub-bands via a multi-level discrete wavelet…

Reference Expression Segmentation (RES) aims to segment image regions specified by referring expressions and has become popular with the rise of multimodal large models (MLLMs). While MLLMs excel in semantic understanding, their…

Predicting protein function from amino acid sequence remains a central challenge in data-scarce (low-$N$) regimes, limiting machine learning-guided protein design when only small amounts of assay-labeled sequence-function data are…

Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech…

Second pass rescoring is a critical component of competitive automatic speech recognition (ASR) systems. Large language models have demonstrated their ability in using pre-trained information for better rescoring of ASR hypothesis.…

Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing. We propose an acoustic data-driven subword modeling (ADSM) approach that…

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping…

Conventional deep neural network (DNN)-based speech enhancement (SE) approaches aim to minimize the mean square error (MSE) between enhanced speech and clean reference. The MSE-optimized model may not directly improve the performance of an…

Recent advancements in automatic speech recognition (ASR) have achieved notable progress, whereas robustness in noisy environments remains challenging. While speech enhancement (SE) front-ends are widely used to mitigate noise as a…

End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic…

Speaker identification typically involves three stages. First, a front-end speaker embedding model is trained to embed utterance and speaker profiles. Second, a scoring function is applied between a runtime utterance and each speaker…

We consider the communication of natural language text from a source to a destination over noiseless and character-erasure channels. We exploit language's inherent correlations and predictability to constrain transmission costs by allowing…

Spatial information is a critical clue for multi-channel multi-speaker target speech recognition. Most state-of-the-art multi-channel Automatic Speech Recognition (ASR) systems extract spatial features only during the speech separation…

This paper presents our recent effort on end-to-end speaker-attributed automatic speech recognition, which jointly performs speaker counting, speech recognition and speaker identification for monaural multi-talker audio. Firstly, we…

Contrastive learning has been studied for improving the performance of learning sentence embeddings. The current state-of-the-art method is the SimCSE, which takes dropout as the data augmentation method and feeds a pre-trained transformer…

Recently, deep neural network (DNN)-based speech enhancement (SE) systems have been used with great success. During training, such systems require clean speech data - ideally, in large quantity with a variety of acoustic conditions, many…

For sequence transduction tasks like speech recognition, a strong structured prior model encodes rich information about the target space, implicitly ruling out invalid sequences by assigning them low probability. In this work, we propose…

Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition (ASR) systems. In this work, we propose Masked Audio Text Encoder (MATE), a multi-modal masked language model rescorer which…

Reward models (RMs) are essential for aligning Large Language Models (LLMs) with human preferences. However, they often struggle with capturing complex human preferences and generalizing to unseen data. To address these challenges, we…