相关论文: Efficient Transformer-based Speech Enhancement Usi…

Streaming speech enhancement is a crucial task for real-time applications such as online meetings, smart home appliances, and hearing aids. Deep neural network-based approaches achieve exceptional performance while demanding substantial…

In this work, we present DeFTAN-II, an efficient multichannel speech enhancement model based on transformer architecture and subgroup processing. Despite the success of transformers in speech enhancement, they face challenges in capturing…

For most of the state-of-the-art speech enhancement techniques, a spectrogram is usually preferred than the respective time-domain raw data since it reveals more compact presentation together with conspicuous temporal information over a…

Recently, speech enhancement technologies that are based on deep learning have received considerable research attention. If the spatial information in microphone signals is exploited, microphone arrays can be advantageous under some adverse…

Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may…

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…

This paper proposes a generative pretraining foundation model for high-quality speech restoration tasks. By directly operating on complex-valued short-time Fourier transform coefficients, our model does not rely on any vocoders for…

Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained…

Semantic segmentation usually benefits from global contexts, fine localisation information, multi-scale features, etc. To advance Transformer-based segmenters with these aspects, we present a simple yet powerful semantic segmentation…

In this paper, we summarize the application of transformer and its streamable variant, Emformer based acoustic model for large scale speech recognition applications. We compare the transformer based acoustic models with their LSTM…

Transformer model architectures have garnered immense interest lately due to their effectiveness across a range of domains like language, vision and reinforcement learning. In the field of natural language processing for example,…

In this work, we introduce S4M, a new efficient speech separation framework based on neural state-space models (SSM). Motivated by linear time-invariant systems for sequence modeling, our SSM-based approach can efficiently model input…

We propose a method using a long short-term memory (LSTM) network to estimate the noise power spectral density (PSD) of single-channel audio signals represented in the short time Fourier transform (STFT) domain. An LSTM network common to…

Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the…

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…

This paper introduces a quantum-inspired denoising framework that integrates the Quantum Fourier Transform (QFT) into classical audio enhancement pipelines. Unlike conventional Fast Fourier Transform (FFT) based methods, QFT provides a…

Transformer-based language models (LMs) pretrained on large text collections are proven to store a wealth of semantic knowledge. However, 1) they are not effective as sentence encoders when used off-the-shelf, and 2) thus typically lag…

In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage…

While deep reinforcement learning (RL) has been demonstrated effective in solving complex control tasks, sample efficiency remains a key challenge due to the large amounts of data required for remarkable performance. Existing research…

The source separation-based speech enhancement problem with multiple beamforming in reverberant indoor environments is addressed in this paper. We propose that more generic solutions should cope with time-varying dynamic scenarios with…