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

The combined electric and acoustic stimulation (EAS) has demonstrated better speech recognition than conventional cochlear implant (CI) and yielded satisfactory performance under quiet conditions. However, when noise signals are involved,…

FullSubNet is our recently proposed real-time single-channel speech enhancement network that achieves outstanding performance on the Deep Noise Suppression (DNS) Challenge dataset. A number of variants of FullSubNet have been proposed, but…

Transformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long sequences, like in…

This paper proposes a model for transforming speech features using the frequency-directional attention model for End-to-End (E2E) automatic speech recognition. The idea is based on the hypothesis that in the phoneme system of each language,…

This paper proposes a speech enhancement method which exploits the high potential of residual connections in a Wide Residual Network architecture. This is supported on single dimensional convolutions computed alongside the time domain,…

Attention mechanisms, such as local and non-local attention, play a fundamental role in recent deep learning based speech enhancement (SE) systems. However, natural speech contains many fast-changing and relatively brief acoustic events,…

We study device-addressed speech detection under pre-ASR edge deployment constraints, where systems must decide whether to forward audio before transcription under strict latency and compute limits. We show that, in multi-speaker…

Curriculum learning begins to thrive in the speech enhancement area, which decouples the original spectrum estimation task into multiple easier sub-tasks to achieve better performance. Motivated by that, we propose a dual-branch…

Attention mechanism is a significant part of Transformer models. It helps extract features from embedded vectors by adding global information and its expressivity has been proved to be powerful. Nevertheless, the quadratic complexity…

Perceptually-inspired objective functions such as the perceptual evaluation of speech quality (PESQ), signal-to-distortion ratio (SDR), and short-time objective intelligibility (STOI), have recently been used to optimize performance of…

Transformer has achieved remarkable success in language, image, and speech processing. Recently, various efficient attention architectures have been proposed to improve transformer's efficiency while largely preserving its efficacy,…

This work aims to investigate the use of a recently proposed, attention-free, scalable state-space model (SSM), Mamba, for the speech enhancement (SE) task. In particular, we employ Mamba to deploy different regression-based SE models…

General speech restoration demands techniques that can interpret complex speech structures under various distortions. While State-Space Models like SEMamba have advanced the state-of-the-art in speech denoising, they are not inherently…

LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify…

We explore on various attention methods on frequency and channel dimensions for sound event detection (SED) in order to enhance performance with minimal increase in computational cost while leveraging domain knowledge to address the…

Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice.…

The task of partially spoofed audio localization aims to accurately determine audio authenticity at a frame level. Although some works have achieved encouraging results, utilizing boundary information within a single model remains an…

Current speech enhancement (SE) research has largely neglected channel attention and spatial attention, and encoder-decoder architecture-based networks have not adequately considered how to provide efficient inputs to the intermediate…

Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion. On the…

The attention mechanism is a core component of the Transformer architecture. Various methods have been developed to compute attention scores, including multi-head attention (MHA), multi-query attention, group-query attention and so on. We…