Related papers: Multi-Task Siamese Neural Network for Improving Re…

Open environment oriented open set model attribution of deepfake audio is an emerging research topic, aiming to identify the generation models of deepfake audio. Most previous work requires manually setting a rejection threshold for unknown…

Advances in automatic speaker verification (ASV) promote research into the formulation of spoofing detection systems for real-world applications. The performance of ASV systems can be degraded severely by multiple types of spoofing attacks,…

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output…

Retrieval-augmented generation (RAG) systems are increasingly deployed in sensitive domains such as healthcare and law, where they rely on private, domain-specific knowledge. This capability introduces significant security risks, including…

Speaker extraction aims to extract target speech signal from a multi-talker environment with interference speakers and surrounding noise, given the target speaker's reference information. Most speaker extraction systems achieve satisfactory…

In this work, we investigate the generalization of a multi-channel learning-based replay speech detector, which employs adaptive beamforming and detection, across different microphone arrays. In general, deep neural network-based microphone…

\textbf{RE}trieval-\textbf{A}ugmented \textbf{L}LM-based \textbf{M}achine \textbf{T}ranslation (REAL-MT) shows promise for knowledge-intensive tasks like idiomatic translation, but its reliability under noisy retrieval contexts remains…

Representation-based multi-task learning (MTL) improves efficiency by learning a shared structure across tasks, but its practical application is often hindered by contamination, outliers, or adversarial tasks. Most existing methods and…

It becomes urgent to design effective anti-spoofing algorithms for vulnerable automatic speaker verification systems due to the advancement of high-quality playback devices. Current studies mainly treat anti-spoofing as a binary…

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common application. These models excel at multi-step reasoning tasks, but their safety properties are not…

Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…

Recently, recurrent neural networks (RNNs) as powerful sequence models have re-emerged as a potential acoustic model for statistical parametric speech synthesis (SPSS). The long short-term memory (LSTM) architecture is particularly…

One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency. Compared to single agent RL, the sample efficiency for Multi-Agent Reinforcement Learning (MARL) is more challenging because of its inherent partial…

Existing speaker verification (SV) systems often suffer from performance degradation if there is any language mismatch between model training, speaker enrollment, and test. A major cause of this degradation is that most existing SV methods…

Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as…

We present Bifocal RNN-T, a new variant of the Recurrent Neural Network Transducer (RNN-T) architecture designed for improved inference time latency on speech recognition tasks. The architecture enables a dynamic pivot for its runtime…

Multilingual speaker verification introduces the challenge of verifying a speaker in multiple languages. Existing systems were built using i-vector/x-vector approaches along with Bi-LSTMs, which were trained to discriminate speakers,…

This paper explores the application of spiking neural networks (SNNs), known for their low-power binary spikes, to bearing fault diagnosis, bridging the gap between high-performance AI algorithms and real-world industrial scenarios. In…

Acoustic echo degrades the user experience in voice communication systems thus needs to be suppressed completely. We propose a real-time residual acoustic echo suppression (RAES) method using an efficient convolutional neural network. The…