Search

Full-duplex spoken dialogue systems significantly advance over traditional turn-based dialogue systems, as they allow simultaneous bidirectional communication, closely mirroring human-human interactions. However, achieving low latency and natural interactions in full-duplex dialogue systems remains a significant challenge, especially considering human conversation dynamics such as interruptions, backchannels, and overlapping speech. In this paper, we introduce a novel End-to-End GPT-based model OmniFlatten for full-duplex conversation, capable of effectively modeling the complex behaviors inherent to natural conversations with low latency. To achieve full-duplex communication capabilities, we propose a multi-stage post-training scheme that progressively adapts a text-based large language model (LLM) backbone into a speech-text dialogue LLM, capable of generating text and speech in real time, without modifying the architecture of the backbone LLM. The training process comprises three stages: modality alignment, half-duplex dialogue learning, and full-duplex dialogue learning. Throughout all training stages, we standardize the data using a flattening operation, which allows us to unify the training methods and the model architecture across different modalities and tasks. Our approach offers a straightforward modeling technique and a promising research direction for developing efficient and natural end-to-end full-duplex spoken dialogue systems. Audio samples of dialogues generated by OmniFlatten can be found at this web site (https://omniflatten.github.io/)., Comment: Work in progress

Metagratings (MGs) have emerged as a promising platform for manipulating the anomalous propagation of electromagnetic waves. However, traditional methods for designing functional MG-based devices face significant challenges, including complex model structures, time-consuming optimization processes, and specific polarization requirements. In this work, we propose an inverse-design approach to engineer simple MG structures comprising periodic air grooves on a flat metal surface, which can control anomalous reflection without polarization limitations. Through rigorous analytical methods, we derive solutions that achieve perfect retroreflection and perfect specular reflection, thereby leading to functional control over the linearly-polarized electromagnetic waves. Such capabilities enable intriguing functionalities including polarization-dependent retroreflection and polarization-independent retroreflection, as confirmed through full-wave simulations. Our work offers a simple and effective method to control freely electromagnetic waves, with potential applications spanning wavefront engineering, polarization splitting, cloaking technologies, and remote sensing.

Automatic Speech Recognition (ASR) transcripts exhibit recognition errors and various spoken language phenomena such as disfluencies, ungrammatical sentences, and incomplete sentences, hence suffering from poor readability. To improve readability, we propose a Contextualized Spoken-to-Written conversion (CoS2W) task to address ASR and grammar errors and also transfer the informal text into the formal style with content preserved, utilizing contexts and auxiliary information. This task naturally matches the in-context learning capabilities of Large Language Models (LLMs). To facilitate comprehensive comparisons of various LLMs, we construct a document-level Spoken-to-Written conversion of ASR Transcripts Benchmark (SWAB) dataset. Using SWAB, we study the impact of different granularity levels on the CoS2W performance, and propose methods to exploit contexts and auxiliary information to enhance the outputs. Experimental results reveal that LLMs have the potential to excel in the CoS2W task, particularly in grammaticality and formality, our methods achieve effective understanding of contexts and auxiliary information by LLMs. We further investigate the effectiveness of using LLMs as evaluators and find that LLM evaluators show strong correlations with human evaluations on rankings of faithfulness and formality, which validates the reliability of LLM evaluators for the CoS2W task., Comment: 7 pages, 3 figures

The video topic segmentation (VTS) task segments videos into intelligible, non-overlapping topics, facilitating efficient comprehension of video content and quick access to specific content. VTS is also critical to various downstream video understanding tasks. Traditional VTS methods using shallow features or unsupervised approaches struggle to accurately discern the nuances of topical transitions. Recently, supervised approaches have achieved superior performance on video action or scene segmentation over unsupervised approaches. In this work, we improve supervised VTS by thoroughly exploring multimodal fusion and multimodal coherence modeling. Specifically, (1) we enhance multimodal fusion by exploring different architectures using cross-attention and mixture of experts. (2) To generally strengthen multimodality alignment and fusion, we pre-train and fine-tune the model with multimodal contrastive learning. (3) We propose a new pre-training task tailored for the VTS task, and a novel fine-tuning task for enhancing multimodal coherence modeling for VTS. We evaluate the proposed approaches on educational videos, in the form of lectures, due to the vital role of topic segmentation of educational videos in boosting learning experiences. Additionally, we introduce a large-scale Chinese lecture video dataset to augment the existing English corpus, promoting further research in VTS. Experiments on both English and Chinese lecture datasets demonstrate that our model achieves superior VTS performance compared to competitive unsupervised and supervised baselines.

The Transformer architecture has significantly advanced deep learning, particularly in natural language processing, by effectively managing long-range dependencies. However, as the demand for understanding complex relationships grows, refining the Transformer's architecture becomes critical. This paper introduces Skip-Layer Attention (SLA) to enhance Transformer models by enabling direct attention between non-adjacent layers. This method improves the model's ability to capture dependencies between high-level abstract features and low-level details. By facilitating direct attention between these diverse feature levels, our approach overcomes the limitations of current Transformers, which often rely on suboptimal intra-layer attention. Our implementation extends the Transformer's functionality by enabling queries in a given layer to interact with keys and values from both the current layer and one preceding layer, thus enhancing the diversity of multi-head attention without additional computational burden. Extensive experiments demonstrate that our enhanced Transformer model achieves superior performance in language modeling tasks, highlighting the effectiveness of our skip-layer attention mechanism., Comment: 7 pages, 1 figure

Recent advancements in large-scale models have showcased remarkable generalization capabilities in various tasks. However, integrating multimodal processing into these models presents a significant challenge, as it often comes with a high computational burden. To address this challenge, we introduce a new parameter-efficient multimodal tuning strategy for large models in this paper, referred to as Multimodal Infusion Tuning (MiT). MiT leverages decoupled self-attention mechanisms within large language models to effectively integrate information from diverse modalities such as images and acoustics. In MiT, we also design a novel adaptive rescaling strategy at the attention head level, which optimizes the representation of infused multimodal features. Notably, all foundation models are kept frozen during the tuning process to reduce the computational burden and only 2.5\% parameters are tunable. We conduct experiments across a range of multimodal tasks, including image-related tasks like referring segmentation and non-image tasks such as sentiment analysis. Our results showcase that MiT achieves state-of-the-art performance in multimodal understanding while significantly reducing computational overhead(10\% of previous methods). Moreover, our tuned model exhibits robust reasoning abilities even in complex scenarios.

Understanding human perceptions presents a formidable multimodal challenge for computers, encompassing aspects such as sentiment tendencies and sense of humor. While various methods have recently been introduced to extract modality-invariant and specific information from diverse modalities, with the goal of enhancing the efficacy of multimodal learning, few works emphasize this aspect in large language models. In this paper, we introduce a novel multimodal prompt strategy tailored for tuning large language models. Our method assesses the correlation among different modalities and isolates the modality-invariant and specific components, which are then utilized for prompt tuning. This approach enables large language models to efficiently and effectively assimilate information from various modalities. Furthermore, our strategy is designed with scalability in mind, allowing the integration of features from any modality into pretrained large language models. Experimental results on public datasets demonstrate that our proposed method significantly improves performance compared to previous methods.

Recently, unified speech-text models, such as SpeechGPT, VioLA, and AudioPaLM, have achieved remarkable performance on various speech tasks. These models discretize speech signals into tokens (speech discretization) and use a shared vocabulary for both text and speech tokens. Then they train a single decoder-only Transformer on a mixture of speech tasks. However, these models rely on the Loss Masking strategy for the ASR task, which ignores the dependency among speech tokens. In this paper, we propose to model speech tokens in an autoregressive way, similar to text. We find that applying the conventional cross-entropy loss on input speech tokens does not consistently improve the ASR performance over the Loss Masking approach. To address this issue, we propose a novel approach denoted Smoothed Label Distillation (SLD), which applies a KL divergence loss with smoothed labels on speech tokens. Our experiments show that SLD effectively models speech tokens and outperforms Loss Masking for decoder-only Transformers in ASR tasks with different speech discretization methods. The source code can be found here: https://github.com/alibaba-damo-academy/SpokenNLP/tree/main/sld, Comment: 5 pages, accepted by ICASSP 2024

Topic segmentation is critical for obtaining structured documents and improving downstream tasks such as information retrieval. Due to its ability of automatically exploring clues of topic shift from abundant labeled data, recent supervised neural models have greatly promoted the development of long document topic segmentation, but leaving the deeper relationship between coherence and topic segmentation underexplored. Therefore, this paper enhances the ability of supervised models to capture coherence from both logical structure and semantic similarity perspectives to further improve the topic segmentation performance, proposing Topic-aware Sentence Structure Prediction (TSSP) and Contrastive Semantic Similarity Learning (CSSL). Specifically, the TSSP task is proposed to force the model to comprehend structural information by learning the original relations between adjacent sentences in a disarrayed document, which is constructed by jointly disrupting the original document at topic and sentence levels. Moreover, we utilize inter- and intra-topic information to construct contrastive samples and design the CSSL objective to ensure that the sentences representations in the same topic have higher similarity, while those in different topics are less similar. Extensive experiments show that the Longformer with our approach significantly outperforms old state-of-the-art (SOTA) methods. Our approach improve $F_1$ of old SOTA by 3.42 (73.74 -> 77.16) and reduces $P_k$ by 1.11 points (15.0 -> 13.89) on WIKI-727K and achieves an average relative reduction of 4.3% on $P_k$ on WikiSection. The average relative $P_k$ drop of 8.38% on two out-of-domain datasets also demonstrates the robustness of our approach., Comment: Accepted by EMNLP 2023. Codes is available at https://github.com/alibaba-damo-academy/SpokenNLP/

Recently, foundation models have been introduced demonstrating various tasks in the field of computer vision. These models such as Segment Anything Model (SAM) are generalized models trained using huge datasets. Currently, ongoing research focuses on exploring the effective utilization of these generalized models for specific domains, such as medical imaging. However, in medical imaging, the lack of training samples due to privacy concerns and other factors presents a major challenge for applying these generalized models to medical image segmentation task. To address this issue, the effective fine tuning of these models is crucial to ensure their optimal utilization. In this study, we propose to combine a complementary Convolutional Neural Network (CNN) along with the standard SAM network for medical image segmentation. To reduce the burden of fine tuning large foundation model and implement cost-efficient trainnig scheme, we focus only on fine-tuning the additional CNN network and SAM decoder part. This strategy significantly reduces trainnig time and achieves competitive results on publicly available dataset. The code is available at https://github.com/11yxk/SAM-LST.

Prior studies diagnose the anisotropy problem in sentence representations from pre-trained language models, e.g., BERT, without fine-tuning. Our analysis reveals that the sentence embeddings from BERT suffer from a bias towards uninformative words, limiting the performance in semantic textual similarity (STS) tasks. To address this bias, we propose a simple and efficient unsupervised approach, Diagonal Attention Pooling (Ditto), which weights words with model-based importance estimations and computes the weighted average of word representations from pre-trained models as sentence embeddings. Ditto can be easily applied to any pre-trained language model as a postprocessing operation. Compared to prior sentence embedding approaches, Ditto does not add parameters nor requires any learning. Empirical evaluations demonstrate that our proposed Ditto can alleviate the anisotropy problem and improve various pre-trained models on STS tasks., Comment: 8 pages, accepted by EMNLP 2023 short paper, the source code can be found at https://github.com/alibaba-damo-academy/SpokenNLP/tree/main/ditto

Meetings are increasingly important for collaborations. Action items in meeting transcripts are crucial for managing post-meeting to-do tasks, which usually are summarized laboriously. The Action Item Detection task aims to automatically detect meeting content associated with action items. However, datasets manually annotated with action item detection labels are scarce and in small scale. We construct and release the first Chinese meeting corpus with manual action item annotations. In addition, we propose a Context-Drop approach to utilize both local and global contexts by contrastive learning, and achieve better accuracy and robustness for action item detection. We also propose a Lightweight Model Ensemble method to exploit different pre-trained models. Experimental results on our Chinese meeting corpus and the English AMI corpus demonstrate the effectiveness of the proposed approaches., Comment: 5 pages, 2 figures. Paper accepted to the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023), Rhodes, Greece

Listening to long video/audio recordings from video conferencing and online courses for acquiring information is extremely inefficient. Even after ASR systems transcribe recordings into long-form spoken language documents, reading ASR transcripts only partly speeds up seeking information. It has been observed that a range of NLP applications, such as keyphrase extraction, topic segmentation, and summarization, significantly improve users' efficiency in grasping important information. The meeting scenario is among the most valuable scenarios for deploying these spoken language processing (SLP) capabilities. However, the lack of large-scale public meeting datasets annotated for these SLP tasks severely hinders their advancement. To prompt SLP advancement, we establish a large-scale general Meeting Understanding and Generation Benchmark (MUG) to benchmark the performance of a wide range of SLP tasks, including topic segmentation, topic-level and session-level extractive summarization and topic title generation, keyphrase extraction, and action item detection. To facilitate the MUG benchmark, we construct and release a large-scale meeting dataset for comprehensive long-form SLP development, the AliMeeting4MUG Corpus, which consists of 654 recorded Mandarin meeting sessions with diverse topic coverage, with manual annotations for SLP tasks on manual transcripts of meeting recordings. To the best of our knowledge, the AliMeeting4MUG Corpus is so far the largest meeting corpus in scale and facilitates most SLP tasks. In this paper, we provide a detailed introduction of this corpus, SLP tasks and evaluation methods, baseline systems and their performance., Comment: Paper accepted to the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023), Rhodes, Greece

ICASSP2023 General Meeting Understanding and Generation Challenge (MUG) focuses on prompting a wide range of spoken language processing (SLP) research on meeting transcripts, as SLP applications are critical to improve users' efficiency in grasping important information in meetings. MUG includes five tracks, including topic segmentation, topic-level and session-level extractive summarization, topic title generation, keyphrase extraction, and action item detection. To facilitate MUG, we construct and release a large-scale meeting dataset, the AliMeeting4MUG Corpus., Comment: Paper accepted to the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023), Rhodes, Greece

Multimodal sentiment analysis and depression estimation are two important research topics that aim to predict human mental states using multimodal data. Previous research has focused on developing effective fusion strategies for exchanging and integrating mind-related information from different modalities. Some MLP-based techniques have recently achieved considerable success in a variety of computer vision tasks. Inspired by this, we explore multimodal approaches with a feature-mixing perspective in this study. To this end, we introduce CubeMLP, a multimodal feature processing framework based entirely on MLP. CubeMLP consists of three independent MLP units, each of which has two affine transformations. CubeMLP accepts all relevant modality features as input and mixes them across three axes. After extracting the characteristics using CubeMLP, the mixed multimodal features are flattened for task predictions. Our experiments are conducted on sentiment analysis datasets: CMU-MOSI and CMU-MOSEI, and depression estimation dataset: AVEC2019. The results show that CubeMLP can achieve state-of-the-art performance with a much lower computing cost., Comment: Accepted by ACM MM 2022

Transcripts generated by automatic speech recognition (ASR) systems for spoken documents lack structural annotations such as paragraphs, significantly reducing their readability. Automatically predicting paragraph segmentation for spoken documents may both improve readability and downstream NLP performance such as summarization and machine reading comprehension. We propose a sequence model with self-adaptive sliding window for accurate and efficient paragraph segmentation. We also propose an approach to exploit phonetic information, which significantly improves robustness of spoken document segmentation to ASR errors. Evaluations are conducted on the English Wiki-727K document segmentation benchmark, a Chinese Wikipedia-based document segmentation dataset we created, and an in-house Chinese spoken document dataset. Our proposed model outperforms the state-of-the-art (SOTA) model based on the same BERT-Base, increasing segmentation F1 on the English benchmark by 4.2 points and on Chinese datasets by 4.3-10.1 points, while reducing inference time to less than 1/6 of inference time of the current SOTA., Comment: accepted by ASRU 2021