相关论文: Windowed SummaryMixing: An Efficient Fine-Tuning o…

Scarcity of pixel-level labels is a significant challenge in practical scenarios. In specific domains like industrial smoke, acquiring such detailed annotations is particularly difficult and often requires expert knowledge. To alleviate…

When dealing with overlapped speech, the performance of automatic speech recognition (ASR) systems substantially degrades as they are designed for single-talker speech. To enhance ASR performance in conversational or meeting environments,…

Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice.…

Semi-supervised learning (SSL) is a widely used technique in scenarios where labeled data is scarce and unlabeled data is abundant. While SSL is popular for image and text classification, it is relatively underexplored for the task of…

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance…

In multi-channel speech enhancement and robust automatic speech recognition (ASR), beamforming can typically improve the signal-to-noise ratio (SNR) of the target speaker and produce reliable enhancement with little distortion to target…

Fine-tuning of Large Language Models (LLMs) for downstream tasks, performed on domain-specific data has shown significant promise. However, commercial use of such LLMs is limited by the high computational cost required for their deployment…

The current dominant approach for neural speech enhancement is based on supervised learning by using simulated training data. The trained models, however, often exhibit limited generalizability to real-recorded data. To address this, this…

This paper proposes a low algorithmic latency adaptation of the deep clustering approach to speaker-independent speech separation. It consists of three parts: a) the usage of long-short-term-memory (LSTM) networks instead of their…

Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global…

Effective image and sentence matching depends on how to well measure their global visual-semantic similarity. Based on the observation that such a global similarity arises from a complex aggregation of multiple local similarities between…

Recent progress in speech recognition has relied on models trained on vast amounts of labeled data. However, classroom Automatic Speech Recognition (ASR) faces the real-world challenge of abundant weak transcripts paired with only a small…

Large Language Models (LLMs) are increasingly deployed across edge and cloud platforms for real-time question-answering and retrieval-augmented generation. However, processing lengthy contexts in distributed systems incurs high…

Multimodal sentiment analysis has attracted increasing attention and lots of models have been proposed. However, the performance of the state-of-the-art models decreases sharply when they are deployed in the real world. We find that the…

Self-Supervised Learning (SSL) has demonstrated strong performance in speech processing, particularly in automatic speech recognition. In this paper, we explore an SSL pretraining framework that leverages masked language modeling with…

Whole Slide Images (WSIs) are giga-pixel in scale and are typically partitioned into small instances in WSI classification pipelines for computational feasibility. However, obtaining extensive instance level annotations is costly, making…

Automatic Speech Recognition (ASR) has witnessed a profound research interest. Recent breakthroughs have given ASR systems different prospects such as faithfully transcribing spoken language, which is a pivotal advancement in building…

Transformer-based Large Language Models (LLMs) often impose limitations on the length of the text input to ensure the generation of fluent and relevant responses. This constraint restricts their applicability in scenarios involving long…

Self-supervised learning representation (SSLR) has demonstrated its significant effectiveness in automatic speech recognition (ASR), mainly with clean speech. Recent work pointed out the strength of integrating SSLR with single-channel…

Large language models (LLMs) have achieved state-of-the-art performance in various language processing tasks, motivating their adoption in simultaneous translation. Current fine-tuning methods to adapt LLMs for simultaneous translation…