17 accepted papers
Audio deep reasoning is a challenging task that requires expert-level perception, multi-step logical inference, and the integration of contextual knowledge. However, existing models suffer from a gap between audio perception and reasoning abilities due to the lack of training data with explicit reas…
Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning utilizing rule-based rewards. However, the explicit reasoning process has not yet yielded su
Automatic Cued Speech Recognition (ACSR) is a vital communication system designed to enhance spoken language accessibility for the hearing-impaired by combining lip movements and hand gestures to encode phonemes. Despite its effectiveness, current ACSR methods face significant challenges, including
Video Scene Graph Generation aims to obtain structured semantic representations of objects and their relationships in videos for high-level understanding. However, existing methods still have limitations in handling long-tail distributions. This paper proposes the Frequency-guided Relational Multi-l…
Achieving zero-shot adversarial robustness without sacrificing generalization remains challenging for foundation models such as CLIP, especially under large adversarial perturbations. Through empirical analyses, we identify three critical yet overlooked issues: (1) Logit margins exhibit a stable off
Cued Speech (CS) enhances lipreading via hand coding, offering visual phonemic cues that support precise speech perception for the hearing-impaired. The task of CS Video-to-Speech generation (CSV2S) aims to convert CS videos into intelligible speech signals. Most existing research focuses on CS Reco
In recent years, speech diffusion models have advanced rapidly. Alongside the widely used U-Net architecture, transformer-based models such as the Diffusion Transformer (DiT) have also gained attention. However, current DiT speech models treat Mel spectrograms as general images, which overlooks the…
Multimodal Continual Instruction Tuning (MCIT) aims to finetune Multimodal Large Language Models (MLLMs) to continually align with human intent across sequential tasks. Existing approaches often rely on the Mixture-of-Experts (MoE) LoRA framework to preserve previous instruction alignments. However,…
Speech synthesis technology has posed a serious threat to speaker verification systems. Currently, the most effective fake audio detection methods utilize pretrained models, and integrating features from various layers of pretrained model further enhances detection performance. However, most of the…
Visual and auditory perception are two crucial ways humans experience the world. Text-to-video generation has made remarkable progress over the past year, but the absence of harmonious audio in generated video limits its broader applications. In this paper, we propose Semantic and Temporal Aligned V…
Current speaker verification techniques heavily rely on the utilization of neural networks to extract accurate and discriminative speaker representations. In this paper, we present Branchformer based TDNN (B-TDNN), a novel architecture for extracting speaker embeddings by capturing both global and l…
In the past year, MultiModal Large Language Models (MM-LLMs) have undergone substantial advancements, augmenting off-the-shelf LLMs to support MM inputs or outputs via cost-effective training strategies. The resulting models not only preserve the inherent reasoning and decision-making capabilities o…
Audio editing involves the arbitrary manipulation of audio content through precise control. Although text-guided diffusion models have made significant advancements in text-to-audio generation, they still face challenges in finding a flexible and precise way to modify target events within an audio t…
In this paper, we propose a Conformer-based network to improve the performance of multi-task audio source separation. This network, named EAD-Conformer, employs Conformer blocks to capture both local and global information, and an encoder-attention-decoder manner encourages the network to perform at…
Voice conversion (VC) is a task to convert the voice of speech while preserving its linguistic content. Although several methods have been proposed to enable VC with non-parallel data, it is still difficult to model the voice without a great number of data or an adaptive process. In this paper, we p…
Most speech separation methods, trying to separate all channel sources simultaneously, are still far from having enough generalization capabilities for real scenarios where the number of input sounds is usually uncertain and even dynamic. In this work, we employ ideas from auditory attention with tw…
In this paper, we propose a speaker-independent multi-speaker monaural speech separation system (CBLDNN-GAT) based on convolutional, bidirectional long short-term memory, deep feedforward neural network (CBLDNN) with generative adversarial training (GAT). Our system aims at obtaining better speech q…