2024-01-05 更新

Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition

Authors:David M. Chan, Shalini Ghosh, Hitesh Tulsiani, Ariya Rastrow, Björn Hoffmeister

While word error rates of automatic speech recognition (ASR) systems have consistently fallen, natural language understanding (NLU) applications built on top of ASR systems still attribute significant numbers of failures to low-quality speech recognition results. Existing assistant systems collect large numbers of these unsuccessful interactions, but these systems usually fail to learn from these interactions, even in an offline fashion. In this work, we introduce CLC: Contrastive Learning for Conversations, a family of methods for contrastive fine-tuning of models in a self-supervised fashion, making use of easily detectable artifacts in unsuccessful conversations with assistants. We demonstrate that our CLC family of approaches can improve the performance of ASR models on OD3, a new public large-scale semi-synthetic meta-dataset of audio task-oriented dialogues, by up to 19.2%. These gains transfer to real-world systems as well, where we show that CLC can help to improve performance by up to 6.7% over baselines. We make OD3 publicly available at https://github.com/amazon-science/amazon-od3 .
PDF To appear in ICASSP 2024


2024-01-05 更新

emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation

Authors:Ziyang Ma, Zhisheng Zheng, Jiaxin Ye, Jinchao Li, Zhifu Gao, Shiliang Zhang, Xie Chen

We propose emotion2vec, a universal speech emotion representation model. emotion2vec is pre-trained on open-source unlabeled emotion data through self-supervised online distillation, combining utterance-level loss and frame-level loss during pre-training. emotion2vec outperforms state-of-the-art pre-trained universal models and emotion specialist models by only training linear layers for the speech emotion recognition task on the mainstream IEMOCAP dataset. In addition, emotion2vec shows consistent improvements among 10 different languages of speech emotion recognition datasets. emotion2vec also shows excellent results on other emotion tasks, such as song emotion recognition, emotion prediction in conversation, and sentiment analysis. Comparison experiments, ablation experiments, and visualization comprehensively demonstrate the universal capability of the proposed emotion2vec. To the best of our knowledge, emotion2vec is the first universal representation model in various emotion-related tasks, filling a gap in the field.
PDF Code, checkpoints, and extracted features are available at https://github.com/ddlBoJack/emotion2vec


Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue

Authors:Guan-Ting Lin, Prashanth Gurunath Shivakumar, Ankur Gandhe, Chao-Han Huck Yang, Yile Gu, Shalini Ghosh, Andreas Stolcke, Hung-yi Lee, Ivan Bulyko

Large Language Models (LLMs) have demonstrated superior abilities in tasks such as chatting, reasoning, and question-answering. However, standard LLMs may ignore crucial paralinguistic information, such as sentiment, emotion, and speaking style, which are essential for achieving natural, human-like spoken conversation, especially when such information is conveyed by acoustic cues. We therefore propose Paralinguistics-enhanced Generative Pretrained Transformer (ParalinGPT), an LLM utilizes text and speech modality to better model the linguistic content and paralinguistic attribute of spoken response. The model takes the conversational context of text, speech embeddings, and paralinguistic attributes as input prompts within a serialized multitasking multi-modal framework. Specifically, our framework serializes tasks in the order of current paralinguistic attribute prediction, response paralinguistic attribute prediction, and response text generation with autoregressive conditioning. We utilize the Switchboard-1 corpus, including its sentiment labels to be the paralinguistic attribute, as our spoken dialogue dataset. Experimental results indicate the proposed serialized multitasking method outperforms typical sequence classification techniques on current and response sentiment classification. Furthermore, leveraging conversational context and speech embeddings significantly improves both response text generation and sentiment prediction. Our proposed framework achieves relative improvements of 6.7%, 12.0%, and 3.5% in current sentiment accuracy, response sentiment accuracy, and response text BLEU score, respectively.
PDF Accepted by ICASSP 2024


Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control

Authors:Zunnan Xu, Yachao Zhang, Sicheng Yang, Ronghui Li, Xiu Li

This study aims to improve the generation of 3D gestures by utilizing multimodal information from human speech. Previous studies have focused on incorporating additional modalities to enhance the quality of generated gestures. However, these methods perform poorly when certain modalities are missing during inference. To address this problem, we suggest using speech-derived multimodal priors to improve gesture generation. We introduce a novel method that separates priors from speech and employs multimodal priors as constraints for generating gestures. Our approach utilizes a chain-like modeling method to generate facial blendshapes, body movements, and hand gestures sequentially. Specifically, we incorporate rhythm cues derived from facial deformation and stylization prior based on speech emotions, into the process of generating gestures. By incorporating multimodal priors, our method improves the quality of generated gestures and eliminate the need for expensive setup preparation during inference. Extensive experiments and user studies confirm that our proposed approach achieves state-of-the-art performance.


The NUS-HLT System for ICASSP2024 ICMC-ASR Grand Challenge

Authors:Meng Ge, Yizhou Peng, Yidi Jiang, Jingru Lin, Junyi Ao, Mehmet Sinan Yildirim, Shuai Wang, Haizhou Li, Mengling Feng

This paper summarizes our team’s efforts in both tracks of the ICMC-ASR Challenge for in-car multi-channel automatic speech recognition. Our submitted systems for ICMC-ASR Challenge include the multi-channel front-end enhancement and diarization, training data augmentation, speech recognition modeling with multi-channel branches. Tested on the offical Eval1 and Eval2 set, our best system achieves a relative 34.3% improvement in CER and 56.5% improvement in cpCER, compared to the offical baseline system.
PDF Technical Report. 2 pages. For ICMC-ASR-2023 Challenge


Make BERT-based Chinese Spelling Check Model Enhanced by Layerwise Attention and Gaussian Mixture Model

Authors:Yongchang Cao, Liang He, Zhen Wu, Xinyu Dai

BERT-based models have shown a remarkable ability in the Chinese Spelling Check (CSC) task recently. However, traditional BERT-based methods still suffer from two limitations. First, although previous works have identified that explicit prior knowledge like Part-Of-Speech (POS) tagging can benefit in the CSC task, they neglected the fact that spelling errors inherent in CSC data can lead to incorrect tags and therefore mislead models. Additionally, they ignored the correlation between the implicit hierarchical information encoded by BERT’s intermediate layers and different linguistic phenomena. This results in sub-optimal accuracy. To alleviate the above two issues, we design a heterogeneous knowledge-infused framework to strengthen BERT-based CSC models. To incorporate explicit POS knowledge, we utilize an auxiliary task strategy driven by Gaussian mixture model. Meanwhile, to incorporate implicit hierarchical linguistic knowledge within the encoder, we propose a novel form of n-gram-based layerwise self-attention to generate a multilayer representation. Experimental results show that our proposed framework yields a stable performance boost over four strong baseline models and outperforms the previous state-of-the-art methods on two datasets.
PDF 10 pages, 4 figures, 2023 International Joint Conference on Neural Networks (IJCNN)


Grounding-Prompter: Prompting LLM with Multimodal Information for Temporal Sentence Grounding in Long Videos

Authors:Houlun Chen, Xin Wang, Hong Chen, Zihan Song, Jia Jia, Wenwu Zhu

Temporal Sentence Grounding (TSG), which aims to localize moments from videos based on the given natural language queries, has attracted widespread attention. Existing works are mainly designed for short videos, failing to handle TSG in long videos, which poses two challenges: i) complicated contexts in long videos require temporal reasoning over longer moment sequences, and ii) multiple modalities including textual speech with rich information require special designs for content understanding in long videos. To tackle these challenges, in this work we propose a Grounding-Prompter method, which is capable of conducting TSG in long videos through prompting LLM with multimodal information. In detail, we first transform the TSG task and its multimodal inputs including speech and visual, into compressed task textualization. Furthermore, to enhance temporal reasoning under complicated contexts, a Boundary-Perceptive Prompting strategy is proposed, which contains three folds: i) we design a novel Multiscale Denoising Chain-of-Thought (CoT) to combine global and local semantics with noise filtering step by step, ii) we set up validity principles capable of constraining LLM to generate reasonable predictions following specific formats, and iii) we introduce one-shot In-Context-Learning (ICL) to boost reasoning through imitation, enhancing LLM in TSG task understanding. Experiments demonstrate the state-of-the-art performance of our Grounding-Prompter method, revealing the benefits of prompting LLM with multimodal information for TSG in long videos.


Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion

Authors:Yun Chen, Lingxiao Yang, Qi Chen, Jian-Huang Lai, Xiaohua Xie

Emotional Voice Conversion aims to manipulate a speech according to a given emotion while preserving non-emotion components. Existing approaches cannot well express fine-grained emotional attributes. In this paper, we propose an Attention-based Interactive diseNtangling Network (AINN) that leverages instance-wise emotional knowledge for voice conversion. We introduce a two-stage pipeline to effectively train our network: Stage I utilizes inter-speech contrastive learning to model fine-grained emotion and intra-speech disentanglement learning to better separate emotion and content. In Stage II, we propose to regularize the conversion with a multi-view consistency mechanism. This technique helps us transfer fine-grained emotion and maintain speech content. Extensive experiments show that our AINN outperforms state-of-the-arts in both objective and subjective metrics.
PDF Accepted by INTERSPEECH 2023


EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Masked Audio Gesture Modeling

Authors:Haiyang Liu, Zihao Zhu, Giorgio Becherini, Yichen Peng, Mingyang Su, You Zhou, Naoya Iwamoto, Bo Zheng, Michael J. Black

We propose EMAGE, a framework to generate full-body human gestures from audio and masked gestures, encompassing facial, local body, hands, and global movements. To achieve this, we first introduce BEATX (BEAT-SMPLX-FLAME), a new mesh-level holistic co-speech dataset. BEATX combines MoShed SMPLX body with FLAME head parameters and further refines the modeling of head, neck, and finger movements, offering a community-standardized, high-quality 3D motion captured dataset. EMAGE leverages masked body gesture priors during training to boost inference performance. It involves a Masked Audio Gesture Transformer, facilitating joint training on audio-to-gesture generation and masked gesture reconstruction to effectively encode audio and body gesture hints. Encoded body hints from masked gestures are then separately employed to generate facial and body movements. Moreover, EMAGE adaptively merges speech features from the audio’s rhythm and content and utilizes four compositional VQ-VAEs to enhance the results’ fidelity and diversity. Experiments demonstrate that EMAGE generates holistic gestures with state-of-the-art performance and is flexible in accepting predefined spatial-temporal gesture inputs, generating complete, audio-synchronized results. Our code and dataset are available at https://pantomatrix.github.io/EMAGE/
PDF Project Page: https://pantomatrix.github.io/EMAGE/


A Multi-Task, Multi-Modal Approach for Predicting Categorical and Dimensional Emotions

Authors:Alex-Răzvan Ispas, Théo Deschamps-Berger, Laurence Devillers

Speech emotion recognition (SER) has received a great deal of attention in recent years in the context of spontaneous conversations. While there have been notable results on datasets like the well known corpus of naturalistic dyadic conversations, IEMOCAP, for both the case of categorical and dimensional emotions, there are few papers which try to predict both paradigms at the same time. Therefore, in this work, we aim to highlight the performance contribution of multi-task learning by proposing a multi-task, multi-modal system that predicts categorical and dimensional emotions. The results emphasise the importance of cross-regularisation between the two types of emotions. Our approach consists of a multi-task, multi-modal architecture that uses parallel feature refinement through self-attention for the feature of each modality. In order to fuse the features, our model introduces a set of learnable bridge tokens that merge the acoustic and linguistic features with the help of cross-attention. Our experiments for categorical emotions on 10-fold validation yield results comparable to the current state-of-the-art. In our configuration, our multi-task approach provides better results compared to learning each paradigm separately. On top of that, our best performing model achieves a high result for valence compared to the previous multi-task experiments.
PDF Companion Publication of the 25th International Conference on Multimodal Interaction (pp. 311-317)


文章作者: 木子已
版权声明: 本博客所有文章除特別声明外,均采用 CC BY 4.0 许可协议。转载请注明来源 木子已 !