Related papers: Location-based training for multi-channel talker-i…

This paper focuses on the challenge of jointly optimizing location and path loss exponent (PLE) in distance-dependent noise. Departing from the conventional independent noise model used in localization and path loss exponent estimation…

Speaker adaptive training (SAT) of neural network acoustic models learns models in a way that makes them more suitable for adaptation to test conditions. Conventionally, model-based speaker adaptive training is performed by having a set of…

Longitudinal NLP tasks require reasoning over temporally ordered text to detect persistence and change in human behavior and opinions. However, in-context learning with large language models struggles on tasks where models must integrate…

Spoofing detection systems are typically trained using diverse recordings from multiple speakers, often assuming that the resulting embeddings are independent of speaker identity. However, this assumption remains unverified. In this paper,…

Split learning is a distributed training paradigm where a neural network is partitioned between clients and a server, which allows data to remain at the client while only intermediate activations are shared. Traditional split learning…

In noisy and reverberant environments, the performance of deep learning-based speech separation methods drops dramatically because previous methods are not designed and optimized for such situations. To address this issue, we propose a…

We propose L2T, an advancement of visual instruction tuning (VIT). While VIT equips Multimodal LLMs (MLLMs) with promising multimodal capabilities, the current design choices for VIT often result in overfitting and shortcut learning,…

Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that…

In this paper we describe a speaker diarization system that enables localization and identification of all speakers present in a conversation or meeting. We propose a novel systematic approach to tackle several long-standing challenges in…

In a scenario with multiple persons talking simultaneously, the spatial characteristics of the signals are the most distinct feature for extracting the target signal. In this work, we develop a deep joint spatial-spectral non-linear filter…

Prompt tuning is a promising method to fine-tune a pre-trained language model without retraining its large-scale parameters. Instead, it attaches a soft prompt to the input text, whereby downstream tasks can be well adapted by merely…

In this work, we revisit the Transformer-based pre-trained language models and identify two different types of information confusion in position encoding and model representations, respectively. Firstly, we show that in the relative…

Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in…

Large language models (LLMs) possess extensive knowledge bases and strong reasoning capabilities, making them promising tools for complex, multi-agent planning in embodied environments. However, despite LLMs' advanced abilities and the…

Adversarial domain-invariant training (ADIT) proves to be effective in suppressing the effects of domain variability in acoustic modeling and has led to improved performance in automatic speech recognition (ASR). In ADIT, an auxiliary…

For noisy environments, ensuring the robustness of keyword spotting (KWS) systems is essential. While much research has focused on noisy KWS, less attention has been paid to multi-talker mixed speech scenarios. Unlike the usual cocktail…

This paper introduces an area-based source separation method designed for virtual meeting scenarios. The aim is to preserve speech signals from an unspecified number of sources within a defined spatial area in front of a linear microphone…

Beyond class frequency, we recognize the impact of class-wise relationships among various class-specific predictions and the imbalance in label masks on long-tailed segmentation learning. To address these challenges, we propose an…

While large language models (LLMs) demonstrate impressive capabilities across numerous applications, their robustness remains a critical concern. This paper is motivated by a specific vulnerability: the order sensitivity of LLMs. This…

During the Covid, online meetings have become an indispensable part of our lives. This trend is likely to continue due to their convenience and broad reach. However, background noise from other family members, roommates, office-mates not…