相关论文: Attentive activation function for improving end-to…

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…

Spoken Language Understanding (SLU) is a task that aims to extract semantic information from spoken utterances. Previous research has made progress in end-to-end SLU by using paired speech-text data, such as pre-trained Automatic Speech…

The activation function is at the heart of a deep neural networks nonlinearity; the choice of the function has great impact on the success of training. Currently, many practitioners prefer the Rectified Linear Unit (ReLU) due to its…

Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires…

Recent studies have shown that the choice of activation function can significantly affect the performance of deep learning networks. However, the benefits of novel activation functions have been inconsistent and task dependent, and…

In task-oriented dialogue systems, spoken language understanding (SLU) is a critical component, which consists of two sub-tasks, intent detection and slot filling. Most existing methods focus on the single-intent SLU, where each utterance…

End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. It promises to improve the performance of assistant systems by leveraging acoustic information lost in the intermediate textual…

Spoken language understanding (SLU) is an essential task for machines to understand human speech for better interactions. However, errors from the automatic speech recognizer (ASR) usually hurt the understanding performance. In reality, ASR…

While Vision-Language Models (VLMs) have garnered increasing attention in the AI community due to their promising practical applications, they exhibit persistent hallucination issues, generating outputs misaligned with visual inputs. Recent…

Recently, self-normalizing neural networks (SNNs) have been proposed with the intention to avoid batch or weight normalization. The key step in SNNs is to properly scale the exponential linear unit (referred to as SELU) to inherently…

Finding synthetic artifacts of spoofing data will help the anti-spoofing countermeasures (CMs) system discriminate between spoofed and real speech. The Conformer combines the best of convolutional neural network and the Transformer,…

With the rapid development of speech conversion and speech synthesis algorithms, automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. In recent years, researchers had proposed a number of anti-spoofing methods…

This thesis introduces the sequence to sequence model with Luong's attention mechanism for end-to-end ASR. It also describes various neural network algorithms including Batch normalization, Dropout and Residual network which constitute the…

This paper describes our submitted systems to the ASVspoof 5 Challenge Track 1: Speech Deepfake Detection - Open Condition, which consists of a stand-alone speech deepfake (bonafide vs spoof) detection task. Recently, large-scale…

This paper introduces an active learning (AL) framework for anomalous sound detection (ASD) in machine condition monitoring system. Typically, ASD models are trained solely on normal samples due to the scarcity of anomalous data, leading to…

The increase in computing power and the necessity of AI-assisted decision-making boost the growing application of large language models (LLMs). Along with this, the potential retention of sensitive data of LLMs has spurred increasing…

Selecting the most suitable activation function is a critical factor in the effectiveness of deep learning models, as it influences their learning capacity, stability, and computational efficiency. In recent years, the Gaussian Error Linear…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…

The emergence of large-scale automatic speech recognition (ASR) models such as Whisper has greatly expanded their adoption across diverse real-world applications. Ensuring robustness against even minor input perturbations is therefore…

We introduce sliced ReLU attention, a new attention mechanism that departs structurally from both softmax and its approximation alternatives. Instead of applying a nonlinearity to pairwise dot products, we operate on one-dimensional…