相关论文: Reference-aware SFM layers for intrusive intelligi…

We introduce our submission to the AudioMOS Challenge (AMC) 2025 Track 3: mean opinion score (MOS) prediction for speech with multiple sampling frequencies (SFs). Our submitted model integrates an SF-independent (SFI) convolutional layer…

Although deep learning models have been successfully applied to a variety of tasks, due to the millions of parameters, they are becoming increasingly opaque and complex. In order to establish trust for their widespread commercial use, it is…

Conventional speech spoofing countermeasures (CMs) are designed to make a binary decision on an input trial. However, a CM trained on a closed-set database is theoretically not guaranteed to perform well on unknown spoofing attacks. In some…

Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging. With the availability of large annotated data (Bowman et al., 2015), it has recently become feasible to…

Large Language Models (LLMs) have attracted extensive attention due to their remarkable performance across various tasks. However, the substantial computational and memory requirements of LLM inference pose challenges for deployment in…

Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought. These longer intermediate reasoning…

Speech encoder models are known to model members of some speaker groups (SGs) better than others. However, there has been little work in establishing why this occurs on a technological level. To our knowledge, we present the first layerwise…

As a fundamental task in Information Retrieval and Computational Linguistics, sentence representation has profound implications for a wide range of practical applications such as text clustering, content analysis, question-answering…

Many self-supervised speech models (S3Ms) have been introduced over the last few years, improving performance and data efficiency on various speech tasks. However, these empirical successes alone do not give a complete picture of what is…

Recently, many novel techniques have been introduced to deal with spoofing attacks, and achieve promising countermeasure (CM) performances. However, these works only take the stand-alone CM models into account. Nowadays, a spoofing aware…

Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance…

Conditional masked language model (CMLM) training has proven successful for non-autoregressive and semi-autoregressive sequence generation tasks, such as machine translation. Given a trained CMLM, however, it is not clear what the best…

Prompt injection poses a critical threat to the safe deployment of large language models, yet existing detection approaches are typically evaluated under limited settings that do not reflect real-world operating constraints. In this work,…

While pre-trained language models (LMs) have brought great improvements in many NLP tasks, there is increasing attention to explore capabilities of LMs and interpret their predictions. However, existing works usually focus only on a certain…

This study examines the effectiveness of traditional machine learning classifiers versus deep learning models for detecting the imagined speech using electroencephalogram data. Specifically, we evaluated conventional machine learning…

Speech enhancement has seen great improvement in recent years using end-to-end neural networks. However, most models are agnostic to the spoken phonetic content. Recently, several studies suggested phonetic-aware speech enhancement, mostly…

Large language models (LLMs) inherently operate over a large generation space, yet conventional usage typically reports the most likely generation (MLG) as a point prediction, which underestimates the model's capability: although the…

Despite achieving encouraging results, neural Referring Expression Generation models are often thought to lack transparency. We probed neural Referential Form Selection (RFS) models to find out to what extent the linguistic features…

As audio-first agents become increasingly common in physical AI, conversational robots, and screenless wearables, audio large language models (audio-LLMs) must integrate speaker-specific understanding to support user authorization,…

Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals,…