Related papers: Duality Temporal-channel-frequency Attention Enhan…
Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it often falls short in recognition performance. In this work, we…
Video captioning is a challenging task that captures different visual parts and describes them in sentences, for it requires visual and linguistic coherence. The attention mechanism in the current video captioning method learns to assign…
Speech-based depression detection poses significant challenges for automated detection due to its unique manifestation across individuals and data scarcity. Addressing these challenges, we introduce DAAMAudioCNNLSTM and…
Time delay neural network (TDNN) has been proven to be efficient for speaker verification. One of its successful variants, ECAPA-TDNN, achieved state-of-the-art performance at the cost of much higher computational complexity and slower…
This paper applies the dual-signal transformation LSTM network (DTLN) to the task of real-time acoustic echo cancellation (AEC). The DTLN combines a short-time Fourier transformation and a learned feature representation in a stacked network…
Acoustic scenes are rich and redundant in their content. In this work, we present a spatio-temporal attention pooling layer coupled with a convolutional recurrent neural network to learn from patterns that are discriminative while…
Dual-task dialog language understanding aims to tackle two correlative dialog language understanding tasks simultaneously via leveraging their inherent correlations. In this paper, we put forward a new framework, whose core is relational…
This paper proposes a model that integrates sub-band processing and deep filtering to fully exploit information from the target time-frequency (TF) bin and its surrounding TF bins for single-channel speech enhancement. The sub-band module…
Sound event localization frameworks based on deep neural networks have shown increased robustness with respect to reverberation and noise in comparison to classical parametric approaches. In particular, recurrent architectures that…
Large Language Models (LLMs) have demonstrated remarkable success across diverse fields, establishing a powerful paradigm for complex information processing. This has inspired the integration of speech into LLM frameworks, often by…
Due to the successful application of deep learning, audio spoofing detection has made significant progress. Spoofed audio with speech synthesis or voice conversion can be well detected by many countermeasures. However, an automatic speaker…
Sound event detection (SED) aims to detect when and recognize what sound events happen in an audio clip. Many supervised SED algorithms rely on strongly labelled data which contains the onset and offset annotations of sound events. However,…
We here propose a novel hierarchical transformer model that adeptly integrates the feature extraction capabilities of Convolutional Neural Networks (CNNs) with the advanced representational potential of Vision Transformers (ViTs).…
Bioacoustics data from Passive acoustic monitoring (PAM) poses a unique set of challenges for classification, particularly the limited availability of complete and reliable labels in datasets due to annotation uncertainty, biological…
Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…
In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…
With the rapid advancement of speech generation technologies, the threat posed by speech deepfakes in real-time communication (RTC) scenarios has intensified. However, existing detection studies mainly focus on offline simulations and…
In this paper, we propose to use deep 3-dimensional convolutional networks (3D CNNs) in order to address the challenge of modelling spectro-temporal dynamics for speech emotion recognition (SER). Compared to a hybrid of Convolutional Neural…
In this paper, we present a gated convolutional neural network and a temporal attention-based localization method for audio classification, which won the 1st place in the large-scale weakly supervised sound event detection task of Detection…
Speaker identification systems in a real-world scenario are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples for each enrolled speaker. This paper demonstrates the effectiveness of meta-learning and…