How can we learn unified representations for spoken utterances and their written text? Learning similar representations for semantically similar speech and text is important for speech translation. To this end, we propose ConST, a cross-modal contrastive learning method for end-to-end speech-to-text translation. We evaluate ConST and a variety of previous baselines on a popular benchmark MuST-C. Experiments show that the proposed ConST consistently outperforms the previous methods on, and achieves an average BLEU of 29.4. The analysis further verifies that ConST indeed closes the representation gap of different modalities -- its learned representation improves the accuracy of cross-modal speech-text retrieval from 4% to 88%. Code and models are available at https://github.com/ReneeYe/ConST.
AI Labs, YuanFuDao（元福道AI实验室）；AI Labs, Didi Chuxing（滴滴出行AI实验室）
Self-supervised visual pretraining has shown significant progress recently. Among those methods, SimCLR greatly advanced the state of the art in self-supervised and semi-supervised learning on ImageNet. The input feature representations for speech and visual tasks are both continuous, so it is natural to consider applying similar objective on speech representation learning. In this paper, we propose Speech SimCLR, a new self-supervised objective for speech representation learning. During training, Speech SimCLR applies augmentation on raw speech and its spectrogram. Its objective is the combin…
Steering Speech-Language Models: Training-Free Task Specialization via Contrastive Activation Addition
Univ Toulon, Aix Marseille Univ, LIS, CNRS（土伦大学，艾克斯-马赛大学，LIS，法国国家科学研究中心）；Mila – Quebec AI Institute（Mila – 魁北克人工智能研究所）；Idiap Research Institute（Idiap 研究所）；Sapienza University of Rome（罗马大学）；Brno University of Technology（布尔诺理工大学）；pyannoteAI（pyannoteAI 公司）；Concordia University（康考迪亚大学）；CNRS, ILLS（法国国家科学研究中心，ILLS）
The Ohio State University（俄亥俄州立大学）；IBM Research AI（IBM研究院人工智能部门）
Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from state-of-the-art text-based models like BERT to speech encoder neural networks. This work is a step towards doing the same in a much more efficient and fine-grained manner where we align speech embeddings and BERT embeddings on a token-by-token basis. We introduce a simple yet novel technique that uses a cross-modal attention mechanism to extract token-level contextual emb…
The goal of self-supervised learning (SSL) for automatic speech recognition (ASR) is to learn good speech representations from a large amount of unlabeled speech for the downstream ASR task. However, most SSL frameworks do not consider noise robustness which is crucial for real-world applications. In this paper we propose wav2vec-Switch, a method to encode noise robustness into contextualized representations of speech via contrastive learning. Specifically, we feed original-noisy speech pairs simultaneously into the wav2vec 2.0 network. In addition to the existing contrastive learning task, we…
Embedding paralinguistic properties is a challenging task as there are only a few hours of training data available for domains such as emotional speech. One solution to this problem is to pretrain a general self-supervised speech representation model on large amounts of unlabeled speech. This pretrained model is then finetuned to a specific task. Paralinguistic properties however have notoriously high class variance, making the finetuning ineffective. In this work, we propose a two step approach to this. First we improve the embedding space, then we train an adapter to bridge the gap from the …
Noise robustness is essential for deploying automatic speech recognition (ASR) systems in real-world environments. One way to reduce the effect of noise interference is to employ a preprocessing module that conducts speech enhancement, and then feed the enhanced speech to an ASR backend. In this work, instead of suppressing background noise with a conventional cascaded pipeline, we employ a noise-robust representation learned by a refined self-supervised framework for noisy speech recognition. We propose to combine a reconstruction module with contrastive learning and perform multi-task contin…
More than half of the 7,000 languages in the world are in imminent danger of going extinct. Traditional methods of documenting language proceed by collecting audio data followed by manual annotation by trained linguists at different levels of granularity. This time consuming and painstaking process could benefit from machine learning. Many endangered languages do not have any orthographic form but usually have speakers that are bi-lingual and trained in a high resource language. It is relatively easy to obtain textual translations corresponding to speech. In this work, we provide a multimodal …
Contrastive Predictive Coding (CPC) is a representation learning method that maximizes the mutual information between intermediate latent representations and the output of a given model. It can be used to effectively initialize the encoder of an Automatic Speech Recognition (ASR) model. We present a novel modification of CPC called Guided Contrastive Predictive Coding (GCPC). Our proposed method maximizes the mutual information between representations from a prior-knowledge model and the output of the model being pre-trained, allowing prior knowledge injection during pre-training. We validate …
Facebook AI Research（脸书人工智能研究院）；EHESS（法国高等社会科学研究院）；CNRS（法国国家科学研究中心）；INRIA（法国国家信息与自动化研究所）；ENS-PSL University（巴黎高等师范学院-巴黎文理研究大学）
Contrastive Predictive Coding (CPC), based on predicting future segments of speech based on past segments is emerging as a powerful algorithm for representation learning of speech signal. However, it still under-performs other methods on unsupervised evaluation benchmarks. Here, we introduce WavAugment, a time-domain data augmentation library and find that applying augmentation in the past is generally more efficient and yields better performances than other methods. We find that a combination of pitch modification, additive noise and reverberation substantially increase the performance of CPC…
In the past decade, sarcasm detection has been intensively conducted in a textual scenario. With the popularization of video communication, the analysis in multi-modal scenarios has received much attention in recent years. Therefore, multi-modal sarcasm detection, which aims at detecting sarcasm in video conversations, becomes increasingly hot in both the natural language processing community and the multi-modal analysis community. In this paper, considering that sarcasm is often conveyed through incongruity between modalities (e.g., text expressing a compliment while acoustic tone indicating …
Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learning
Institute for Analytics and Data Science, University of Essex（数据分析与科学研究所，埃塞克斯大学）；School of Computer Science and Electronic Engineering, University of Essex（计算机科学与电子工程学院，埃塞克斯大学）
The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
University of Trento, Italy（特伦托大学，意大利）；Fondazione Bruno Kessler, Italy（布鲁诺·凯塞勒基金会，意大利）；Laboratoire de Linguistique Formelle, Université Paris Cité, CNRS, Paris, France（形式语言实验室，巴黎城市大学，法国国家科学研究中心，法国巴黎）
Spoken language understanding (SLU) is an essential task for machines to understand human speech for better interactions. However, errors from the automatic speech recognizer (ASR) usually hurt the understanding performance. In reality, ASR systems may not be easy to adjust for the target scenarios. Therefore, this paper focuses on learning utterance representations that are robust to ASR errors using a contrastive objective, and further strengthens the generalization ability by combining supervised contrastive learning and self-distillation in model fine-tuning. Experiments on three benchmark…
Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages
Nanyang Technological University（南洋理工大学）；Southwest Jiaotong University（西南交通大学）；Kash Institute of Electronics and Information Industry（Kash电子信息产业研究院）；Southwest Petroleum University（西南石油大学）
We investigate multi-speaker speech recognition from ultrasound images of the tongue and video images of the lips. We train our systems on imaging data from modal speech, and evaluate on matched test sets of two speaking modes: silent and modal speech. We observe that silent speech recognition from imaging data underperforms compared to modal speech recognition, likely due to a speaking-mode mismatch between training and testing. We improve silent speech recognition performance using techniques that address the domain mismatch, such as fMLLR and unsupervised model adaptation. We also analyse t…
Multimodal sentiment analysis has become an increasingly popular research area as the demand for multimodal online content is growing. For multimodal sentiment analysis, words can have different meanings depending on the linguistic context and non-verbal information, so it is crucial to understand the meaning of the words accordingly. In addition, the word meanings should be interpreted within the whole utterance context that includes nonverbal information. In this paper, we present a Context-driven Modality Shifting BERT with Contrastive Learning for linguistic, visual, acoustic Representatio…
Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other. They can only utilize single-modal data (i.e. text or image) or limited multi-modal data (i.e. image-text pairs). In this work, we propose a unified-modal pre-training architecture, namely UNIMO, which can effectively adapt to both single-modal and multi-modal understanding and generation tasks. Large scale of free text corpus and image collections can be utilized to improve the capability of visual and textual understanding, and cross-modal contrastive learning (CM…
Southern University of Science and Technology（南方科技大学）；The Hong Kong Polytechnic University（香港理工大学）；Tongji University（同济大学）；Microsoft（微软）；Peng Cheng Laboratory（鹏城实验室）
Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text mod…
Multi-modal entity alignment aims to identify equivalent entities between two different multi-modal knowledge graphs, which consist of structural triples and images associated with entities. Most previous works focus on how to utilize and encode information from different modalities, while it is not trivial to leverage multi-modal knowledge in entity alignment because of the modality heterogeneity. In this paper, we propose MCLEA, a Multi-modal Contrastive Learning based Entity Alignment model, to obtain effective joint representations for multi-modal entity alignment. Different from previous …
Adversarial Representation with Intra-Modal and Inter-Modal Graph Contrastive Learning for Multimodal Emotion Recognition
School of computer and Information Engineering, Central South University of Forestry and Technology（中南林业科技大学计算机与信息工程学院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；State University of New York（纽约州立大学）
End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due to the modality differences between speech outputs from the encoder and text inputs to the decoder. In this work, we aim to bridge the modality gap between speech and text to improve translation quality. We propose M-Adapter, a novel Transformer-based module, to adapt speech representations to text. While shrinking the speech sequence, M-Adapter produces features desired for sp…
While audio-visual speech models can yield superior performance and robustness compared to audio-only models, their development and adoption are hindered by the lack of labeled and unlabeled audio-visual data and the cost to deploy one model per modality. In this paper, we present u-HuBERT, a self-supervised pre-training framework that can leverage both multimodal and unimodal speech with a unified masked cluster prediction objective. By utilizing modality dropout during pre-training, we demonstrate that a single fine-tuned model can achieve performance on par or better than the state-of-the-a…
We present modality gap, an intriguing geometric phenomenon of the representation space of multi-modal models. Specifically, we show that different data modalities (e.g. images and text) are embedded at arm's length in their shared representation in multi-modal models such as CLIP. Our systematic analysis demonstrates that this gap is caused by a combination of model initialization and contrastive learning optimization. In model initialization, we show empirically and theoretically that the representation of a common deep neural network is restricted to a narrow cone. As a consequence, in a mu…
Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment
Peking University（北京大学）；School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）；School of Computer Science, Peking University（北京大学计算机学院）
Columbia University（哥伦比亚大学）；Microsoft Cloud and AI（微软云与人工智能部门）；Microsoft Research（微软研究院）
Large-scale multi-modal contrastive pre-training has demonstrated great utility to learn transferable features for a range of downstream tasks by mapping multiple modalities into a shared embedding space. Typically, this has employed separate encoders for each modality. However, recent work suggests that transformers can support learning across multiple modalities and allow knowledge sharing. Inspired by this, we investigate a variety of Modality-Shared Contrastive Language-Image Pre-training (MS-CLIP) frameworks. More specifically, we question how many parameters of a transformer model can be…
