相关论文: Local spectral attention for full-band speech enha…

Transformers have become the foundation of numerous state-of-the-art AI models across diverse domains, thanks to their powerful attention mechanism for modeling long-range dependencies. However, the quadratic scaling complexity of attention…

Self-supervised Audio Transformers (SAT) enable great success in many downstream speech applications like ASR, but how they work has not been widely explored yet. In this work, we present multiple strategies for the analysis of attention…

Transformer-based speech recognition models have achieved great success due to the self-attention (SA) mechanism that utilizes every frame in the feature extraction process. Especially, SA heads in lower layers capture various phonetic…

Self-attention models have been successfully applied in end-to-end speech recognition systems, which greatly improve the performance of recognition accuracy. However, such attention-based models cannot be used in online speech recognition,…

This paper proposes an noise type classification aided attention-based neural network approach for monaural speech enhancement. The network is constructed based on a previous work by introducing a noise classification subnetwork into the…

Transformer-based acoustic modeling has achieved great suc-cess for both hybrid and sequence-to-sequence speech recogni-tion. However, it requires access to the full sequence, and thecomputational cost grows quadratically with respect to…

Attention steering is an important technique for controlling model focus, enabling capabilities such as prompt highlighting, where the model prioritises user-specified text. However, existing attention steering methods require explicit…

When the parameters of Bayesian Short-time Spectral Amplitude (STSA) estimator for speech enhancement are selected based on the characteristics of the human auditory system, the gain function of the estimator becomes more flexible. Although…

Machine anomalous sound detection (ASD) is a valuable technique across various applications. However, its generalization performance is often limited due to challenges in data collection and the complexity of acoustic environments. Inspired…

An initial real-time speech enhancement method is presented to reduce the effects of additive noise. The method operates in the frequency domain and is a form of spectral subtraction. Initially, minimum statistics are used to generate an…

Recently, SpecAugment, an augmentation scheme for automatic speech recognition that acts directly on the spectrogram of input utterances, has shown to be highly effective in enhancing the performance of end-to-end networks on public…

Teleconferencing is becoming essential during the COVID-19 pandemic. However, in real-world applications, speech quality can deteriorate due to, for example, background interference, noise, or reverberation. To solve this problem, target…

Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…

Event cameras provide sequential visual data with spatial sparsity and high temporal resolution, making them attractive for low-latency object detection. Existing asynchronous event-based neural networks realize this low-latency advantage…

Self-supervised adaptation (SSA) improves foundation model transfer to medical domains but is computationally prohibitive. Although parameter efficient fine-tuning methods such as LoRA have been explored for supervised adaptation, their…

Transformers have become the leading choice in natural language processing over other deep learning architectures. This trend has also permeated the field of time series analysis, especially for long-horizon forecasting, showcasing…

Speech enhancement methods based on deep learning have surpassed traditional methods. While many of these new approaches are operating on the wideband (16kHz) sample rate, a new fullband (48kHz) speech enhancement system is proposed in this…

While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…

The optimization of a wavelet-based algorithm to improve speech intelligibility along with the full data set and results are reported. The discrete-time speech signal is split into frequency sub-bands via a multi-level discrete wavelet…

Benefiting from its succinctness and robustness, skeleton-based action recognition has recently attracted much attention. Most existing methods utilize local networks (e.g., recurrent, convolutional, and graph convolutional networks) to…