Scaling Transformers for Low-Bitrate High-Quality Speech Coding

The tokenization of speech with neural audio codec models is a vital part of modern AI pipelines for the generation or understanding of speech, alone or in a multimodal context. Traditionally such tokenization models have concentrated on low parameter-count architectures using only components with strong inductive biases. In this work we show that by scaling a transformer architecture with large parameter count to this problem, and applying a flexible Finite Scalar Quantization (FSQ) based bottleneck, it is possible to reach state-of-the-art speech quality at extremely low bit-rates of $400$ or $700$ bits-per-second. The trained models strongly out-perform existing baselines in both objective and subjective tests.

Learning Source Disentanglement in Neural Audio Codec

Neural audio codecs have significantly advanced audio compression by efficiently converting continuous audio signals into discrete tokens. These codecs preserve high-quality sound and enable sophisticated sound generation through generative models trained on these tokens. However, existing neural codec models are typically trained on large, undifferentiated audio datasets, neglecting the essential discrepancies between sound domains like speech, music, and environmental sound effects. This oversight complicates data modeling and poses additional challenges to the controllability of sound generation. To tackle these issues, we introduce the Source-Disentangled Neural Audio Codec (SD-Codec), a novel approach that combines audio coding and source separation. By jointly learning audio resynthesis and separation, SD-Codec explicitly assigns audio signals from different domains to distinct codebooks, sets of discrete representations. Experimental results indicate that SD-Codec not only maintains competitive resynthesis quality but also, supported by the separation results, demonstrates successful disentanglement of different sources in the latent space, thereby enhancing interpretability in audio codec and providing potential finer control over the audio generation process.

FlowSep: Language-Queried Sound Separation with Rectified Flow Matching

Language-queried audio source separation (LASS) focuses on separating sounds using textual descriptions of the desired sources. Current methods mainly use discriminative approaches, such as time-frequency masking, to separate target sounds and minimize interference from other sources. However, these models face challenges when separating overlapping soundtracks, which may lead to artifacts such as spectral holes or incomplete separation. Rectified flow matching (RFM), a generative model that establishes linear relations between the distribution of data and noise, offers superior theoretical properties and simplicity, but has not yet been explored in sound separation. In this work, we introduce FlowSep, a new generative model based on RFM for LASS tasks. FlowSep learns linear flow trajectories from noise to target source features within the variational autoencoder (VAE) latent space. During inference, the RFM-generated latent features are reconstructed into a mel-spectrogram via the pre-trained VAE decoder, followed by a pre-trained vocoder to synthesize the waveform. Trained on 1,680 hours of audio data, FlowSep outperforms the state-of-the-art models across multiple benchmarks, as evaluated with subjective and objective metrics. Additionally, our results show that FlowSep surpasses a diffusion-based LASS model in both separation quality and inference efficiency, highlighting its strong potential for audio source separation tasks. Code, pre-trained models and demos can be found at: https://audio-agi.github.io/FlowSep_demo/.

Universal Sound Separation with Self-Supervised Audio Masked Autoencoder

Universal sound separation (USS) is a task of separating mixtures of arbitrary sound sources. Typically, universal separation models are trained from scratch in a supervised manner, using labeled data. Self-supervised learning (SSL) is an emerging deep learning approach that leverages unlabeled data to obtain task-agnostic representations, which can benefit many downstream tasks. In this paper, we propose integrating a self-supervised pre-trained model, namely the audio masked autoencoder (A-MAE), into a universal sound separation system to enhance its separation performance. We employ two strategies to utilize SSL embeddings: freezing or updating the parameters of A-MAE during fine-tuning. The SSL embeddings are concatenated with the short-time Fourier transform (STFT) to serve as input features for the separation model. We evaluate our methods on the AudioSet dataset, and the experimental results indicate that the proposed methods successfully enhance the separation performance of a state-of-the-art ResUNet-based USS model.

A Reference-free Metric for Language-Queried Audio Source Separation using Contrastive Language-Audio Pretraining

Language-queried audio source separation (LASS) aims to separate an audio source guided by a text query, with the signal-to-distortion ratio (SDR)-based metrics being commonly used to objectively measure the quality of the separated audio. However, the SDR-based metrics require a reference signal, which is often difficult to obtain in real-world scenarios. In addition, with the SDR-based metrics, the content information of the text query is not considered effectively in LASS. This paper introduces a reference-free evaluation metric using a contrastive language-audio pretraining (CLAP) module, termed CLAPScore, which measures the semantic similarity between the separated audio and the text query. Unlike SDR, the proposed CLAPScore metric evaluates the quality of the separated audio based on the content information of the text query, without needing a reference signal. Experimental results show that the CLAPScore metric provides an effective evaluation of the semantic relevance of the separated audio to the text query, as compared to the SDR metric, offering an alternative for the performance evaluation of LASS systems.

Improving Audio Generation with Visual Enhanced Caption

Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performance degradation. We hypothesize that this problem stems from the low quality and relatively small quantity of training data. In this work, we aim to create a large-scale audio dataset with rich captions for improving audio generation models. We develop an automated pipeline to generate detailed captions for audio-visual datasets by transforming predicted visual captions, audio captions, and tagging labels into comprehensive descriptions using a Large Language Model (LLM). We introduce Sound-VECaps, a dataset comprising 1.66M high-quality audio-caption pairs with enriched details including audio event orders, occurred places and environment information. We demonstrate that training with Sound-VECaps significantly enhances the capability of text-to-audio generation models to comprehend and generate audio from complex input prompts, improving overall system performance. Furthermore, we conduct ablation studies of Sound-VECaps across several audio-language tasks, suggesting its potential in advancing audio-text representation learning. Our dataset and models are available online.

Learning Retrieval Augmentation for Personalized Dialogue Generation

Personalized dialogue generation, focusing on generating highly tailored responses by leveraging persona profiles and dialogue context, has gained significant attention in conversational AI applications. However, persona profiles, a prevalent setting in current personalized dialogue datasets, typically composed of merely four to five sentences, may not offer comprehensive descriptions of the persona about the agent, posing a challenge to generate truly personalized dialogues. To handle this problem, we propose $\textbf{L}$earning Retrieval $\textbf{A}$ugmentation for $\textbf{P}$ersonalized $\textbf{D}$ial$\textbf{O}$gue $\textbf{G}$eneration ($\textbf{LAPDOG}$), which studies the potential of leveraging external knowledge for persona dialogue generation. Specifically, the proposed LAPDOG model consists of a story retriever and a dialogue generator. The story retriever uses a given persona profile as queries to retrieve relevant information from the story document, which serves as a supplementary context to augment the persona profile. The dialogue generator utilizes both the dialogue history and the augmented persona profile to generate personalized responses. For optimization, we adopt a joint training framework that collaboratively learns the story retriever and dialogue generator, where the story retriever is optimized towards desired ultimate metrics (e.g., BLEU) to retrieve content for the dialogue generator to generate personalized responses. Experiments conducted on the CONVAI2 dataset with ROCStory as a supplementary data source show that the proposed LAPDOG method substantially outperforms the baselines, indicating the effectiveness of the proposed method. The LAPDOG model code is publicly available for further exploration. https://github.com/hqsiswiliam/LAPDOG

Selective Prompting Tuning for Personalized Conversations with LLMs

In conversational AI, personalizing dialogues with persona profiles and contextual understanding is essential. Despite large language models' (LLMs) improved response coherence, effective persona integration remains a challenge. In this work, we first study two common approaches for personalizing LLMs: textual prompting and direct fine-tuning. We observed that textual prompting often struggles to yield responses that are similar to the ground truths in datasets, while direct fine-tuning tends to produce repetitive or overly generic replies. To alleviate those issues, we propose \textbf{S}elective \textbf{P}rompt \textbf{T}uning (SPT), which softly prompts LLMs for personalized conversations in a selective way. Concretely, SPT initializes a set of soft prompts and uses a trainable dense retriever to adaptively select suitable soft prompts for LLMs according to different input contexts, where the prompt retriever is dynamically updated through feedback from the LLMs. Additionally, we propose context-prompt contrastive learning and prompt fusion learning to encourage the SPT to enhance the diversity of personalized conversations. Experiments on the CONVAI2 dataset demonstrate that SPT significantly enhances response diversity by up to 90\%, along with improvements in other critical performance indicators. Those results highlight the efficacy of SPT in fostering engaging and personalized dialogue generation. The SPT model code (https://github.com/hqsiswiliam/SPT) is publicly available for further exploration.

Fish Tracking, Counting, and Behaviour Analysis in Digital Aquaculture: A Comprehensive Review

Digital aquaculture leverages advanced technologies and data-driven methods, providing substantial benefits over traditional aquaculture practices. Fish tracking, counting, and behaviour analysis are crucial components of digital aquaculture, which are essential for optimizing production efficiency, enhancing fish welfare, and improving resource management. Previous reviews have focused on single modalities, limiting their ability to address the diverse challenges encountered in these tasks comprehensively. This review provides a comprehensive analysis of the current state of aquaculture digital technologies, including vision-based, acoustic-based, and biosensor-based methods. We examine the advantages, limitations, and applications of these methods, highlighting recent advancements and identifying critical research gaps. The scarcity of comprehensive fish datasets and the lack of unified evaluation standards, which make it difficult to compare the performance of different technologies, are identified as major obstacles hindering progress in this field. To overcome current limitations and improve the accuracy, robustness, and efficiency of fish monitoring systems, we explore the potential of emerging technologies such as multimodal data fusion and deep learning. Additionally, we contribute to the field by providing a summary of existing datasets available for fish tracking, counting, and behaviour analysis. Future research directions are outlined, emphasizing the need for comprehensive datasets and evaluation standards to facilitate meaningful comparisons between technologies and promote their practical implementation in real-world aquaculture settings.

Dynamic Identity-Guided Attention Network for Visible-Infrared Person Re-identification

Visible-infrared person re-identification (VI-ReID) aims to match people with the same identity between visible and infrared modalities. VI-ReID is a challenging task due to the large differences in individual appearance under different modalities. Existing methods generally try to bridge the cross-modal differences at image or feature level, which lacks exploring the discriminative embeddings. Effectively minimizing these cross-modal discrepancies relies on obtaining representations that are guided by identity and consistent across modalities, while also filtering out representations that are irrelevant to identity. To address these challenges, we introduce a dynamic identity-guided attention network (DIAN) to mine identity-guided and modality-consistent embeddings, facilitating effective bridging the gap between different modalities. Specifically, in DIAN, to pursue a semantically richer representation, we first use orthogonal projection to fuse the features from two connected coarse and fine layers. Furthermore, we first use dynamic convolution kernels to mine identity-guided and modality-consistent representations. More notably, a cross embedding balancing loss is introduced to effectively bridge cross-modal discrepancies by above embeddings. Experimental results on SYSU-MM01 and RegDB datasets show that DIAN achieves state-of-the-art performance. Specifically, for indoor search on SYSU-MM01, our method achieves 86.28% rank-1 accuracy and 87.41% mAP, respectively. Our code will be available soon.