相关论文: Audio-Visual Speech Separation via Bottleneck Iter…

Under noisy conditions, speech recognition systems suffer from high Word Error Rates (WER). In such cases, information from the visual modality comprising the speaker lip movements can help improve the performance. In this work, we propose…

We propose an independence-based joint dereverberation and separation method with a neural source model. We introduce a neural network in the framework of time-decorrelation iterative source steering, which is an extension of independent…

In this work we aim to discover high quality speech features and linguistic units directly from unlabeled speech data in a zero resource scenario. The results are evaluated using the metrics and corpora proposed in the Zero Resource Speech…

Bidirectional language models have better context understanding and perform better than unidirectional models on natural language understanding tasks, yet the theoretical reasons behind this advantage remain unclear. In this work, we…

Self-supervised audio-visual source separation leverages natural correlations between audio and vision modalities to separate mixed audio signals. In this work, we first systematically analyse the performance of existing multimodal fusion…

We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression objective but also…

The performance of speaker diarization is strongly affected by its clustering algorithm at the test stage. However, it is known that clustering algorithms are sensitive to random noises and small variations, particularly when the clustering…

Audio-visual speech separation methods aim to integrate different modalities to generate high-quality separated speech, thereby enhancing the performance of downstream tasks such as speech recognition. Most existing state-of-the-art (SOTA)…

Deep neural networks suffer from poor generalization to unseen environments when the underlying data distribution is different from that in the training set. By learning minimum sufficient representations from training data, the information…

By implicitly recognizing a user based on his/her speech input, speaker identification enables many downstream applications, such as personalized system behavior and expedited shopping checkouts. Based on whether the speech content is…

Deep neural networks (DNNs) have achieved significant success in various applications with large-scale and balanced data. However, data in real-world visual recognition are usually long-tailed, bringing challenges to efficient training and…

Automatic speech recognition can potentially benefit from the lip motion patterns, complementing acoustic speech to improve the overall recognition performance, particularly in noise. In this paper we propose an audio-visual fusion strategy…

The two-pass information bottleneck (TPIB) based speaker diarization system operates independently on different conversational recordings. TPIB system does not consider previously learned speaker discriminative information while diarizing…

Deep learning systems often struggle with processing long sequences, where computational complexity can become a bottleneck. Current methods for automated dementia detection using speech frequently rely on static, time-agnostic features or…

Multi-modal based speech separation has exhibited a specific advantage on isolating the target character in multi-talker noisy environments. Unfortunately, most of current separation strategies prefer a straightforward fusion based on…

Body-conduction microphone signals (BMS) bypass airborne sound, providing strong noise resistance. However, a complementary modality is required to compensate for the inherent loss of high-frequency information. In this study, we propose a…

Interpreting individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making processes and ensuring AI safety. Despite recent progress in neuron labeling, existing methods often limit the…

Binaural speech enhancement (BSE) aims to jointly improve the speech quality and intelligibility of noisy signals received by hearing devices and preserve the spatial cues of the target for natural listening. Existing methods often suffer…

In this paper, we explore an improved framework to train a monoaural neural enhancement model for robust speech recognition. The designed training framework extends the existing mixture invariant training criterion to exploit both unpaired…

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…