Vision is often used as a complementary modality for audio speech recognition (ASR), especially in the noisy environment where performance of solo audio modality significantly deteriorates. After combining visual modality, ASR is upgraded to the multi-modality speech recognition (MSR). In this paper, we propose a two-stage speech recognition model. In the first stage, the target voice is separated from background noises with help from the corresponding visual information of lip movements, making the model 'listen' clearly. At the second stage, the audio modality combines visual modality again to better understand the speech by a MSR sub-network, further improving the recognition rate. There are some other key contributions: we introduce a pseudo-3D residual convolution (P3D)-based visual front-end to extract more discriminative features; we upgrade the temporal convolution block from 1D ResNet with the temporal convolutional network (TCN), which is more suitable for the temporal tasks; the MSR sub-network is built on the top of Element-wise-Attention Gated Recurrent Unit (EleAtt-GRU), which is more effective than Transformer in long sequences. We conducted extensive experiments on the LRS3-TED and the LRW datasets. Our two-stage model (audio enhanced multi-modality speech recognition, AE-MSR) consistently achieves the state-of-the-art performance by a significant margin, which demonstrates the necessity and effectiveness of AE-MSR.
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…
Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for audio-visual speech recognition which could automatically learn the fused representation from both modalities based on their importance. Our method is realized using state-of-the-art sequence-to-sequence (Seq2seq) architectures. Experimental results show that relative improvements from 2% up to 36% over the auditory modality alone are obtained depending on the di…
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…
Nanyang Technological University（南洋理工大学）；ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙江大学杭州国际科创中心）；Zhejiang University（浙江大学）
Audio-visual speech recognition (AVSR) has gained remarkable success for ameliorating the noise-robustness of speech recognition. Mainstream methods focus on fusing audio and visual inputs to obtain modality-invariant representations. However, such representations are prone to over-reliance on audio modality as it is much easier to recognize than video modality in clean conditions. As a result, the AVSR model underestimates the importance of visual stream in face of noise corruption. To this end, we leverage visual modality-specific representations to provide stable complementary information f…
Second-pass rescoring is an important component in automatic speech recognition (ASR) systems that is used to improve the outputs from a first-pass decoder by implementing a lattice rescoring or $n$-best re-ranking. While pretraining with a masked language model (MLM) objective has received great success in various natural language understanding (NLU) tasks, it has not gained traction as a rescoring model for ASR. Specifically, training a bidirectional model like BERT on a discriminative objective such as minimum WER (MWER) has not been explored. Here we show how to train a BERT-based rescorin…
Institute of Information Science, Academia Sinica（中央研究院信息科学研究所）
In our previous work, we proposed a discriminative autoencoder (DcAE) for speech recognition. DcAE combines two training schemes into one. First, since DcAE aims to learn encoder-decoder mappings, the squared error between the reconstructed speech and the input speech is minimized. Second, in the code layer, frame-based phonetic embeddings are obtained by minimizing the categorical cross-entropy between ground truth labels and predicted triphone-state scores. DcAE is developed based on the Kaldi toolkit by treating various TDNN models as encoders. In this paper, we further propose three new ve…
Institute of Information Science, Academia Sinica（中央研究院信息科学研究所）；Research Center for Information Technology Innovation, Academia Sinica（中央研究院信息科技创新研究中心）
Children speech recognition is indispensable but challenging due to the diversity of children's speech. In this paper, we propose a filter-based discriminative autoencoder for acoustic modeling. To filter out the influence of various speaker types and pitches, auxiliary information of the speaker and pitch features is input into the encoder together with the acoustic features to generate phonetic embeddings. In the training phase, the decoder uses the auxiliary information and the phonetic embedding extracted by the encoder to reconstruct the input acoustic features. The autoencoder is trained…
Self-Powered LLM Modality Expansion for Large Speech-Text Models
Institute of Computing and Intelligence, Harbin Institute of Technology（哈尔滨工业大学计算与智能学院）；Faculty of Computing, Harbin Institute of Technology（哈尔滨工业大学计算机学院）；The University of Sydney（悉尼大学）；Nanyang Technological University（南洋理工大学）
Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（中国科学院智能信息处理重点实验室）；Key Laboratory of AI Safety, Chinese Academy of Sciences（中国科学院人工智能安全重点实验室）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）
We present Maestro, a self-supervised training method to unify representations learnt from speech and text modalities. Self-supervised learning from speech signals aims to learn the latent structure inherent in the signal, while self-supervised learning from text attempts to capture lexical information. Learning aligned representations from unpaired speech and text sequences is a challenging task. Previous work either implicitly enforced the representations learnt from these two modalities to be aligned in the latent space through multitasking and parameter sharing or explicitly through conver…
BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Alibaba Inc.（阿里巴巴集团）；Machine Intelligence Technology Lab, Alibaba Inc.（阿里巴巴集团机器智能技术实验室）；Wuhan AI Research（武汉人工智能研究院）
End-to-end Speech Translation (ST) models have several advantages such as lower latency, smaller model size, and less error compounding over conventional pipelines that combine Automatic Speech Recognition (ASR) and text Machine Translation (MT) models. However, collecting large amounts of parallel data for ST task is more difficult compared to the ASR and MT tasks. Previous studies have proposed the use of transfer learning approaches to overcome the above difficulty. These approaches benefit from weakly supervised training data, such as ASR speech-to-transcript or MT text-to-text translation…
Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs
Fondazione Bruno Kessler（布鲁诺·凯瑟尔基金会）；Barcelona Supercomputing Center（巴塞罗那超级计算中心）；University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；Universitat Politècnica de València（瓦伦西亚理工大学）；Soongsil University（顺天大学）；Charles University（查尔斯大学）；KIT（卡尔斯鲁厄理工学院）
Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）深圳大数据研究院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Automatic Cued Speech Recognition (ACSR) provides an intelligent human-machine interface for visual communications, where the Cued Speech (CS) system utilizes lip movements and hand gestures to code spoken language for hearing-impaired people. Previous ACSR approaches often utilize direct feature concatenation as the main fusion paradigm. However, the asynchronous modalities i.e., lip, hand shape and hand position) in CS may cause interference for feature concatenation. To address this challenge, we propose a transformer based cross-modal mutual learning framework to prompt multi-modal interac…
Punctuation prediction for automatic speech recognition (ASR) output transcripts plays a crucial role for improving the readability of the ASR transcripts and for improving the performance of downstream natural language processing applications. However, achieving good performance on punctuation prediction often requires large amounts of labeled speech transcripts, which is expensive and laborious. In this paper, we propose a Discriminative Self-Training approach with weighted loss and discriminative label smoothing to exploit unlabeled speech transcripts. Experimental results on the English IW…
Speech recognition is a sequence prediction problem. Besides employing various deep learning approaches for framelevel classification, sequence-level discriminative training has been proved to be indispensable to achieve the state-of-the-art performance in large vocabulary continuous speech recognition (LVCSR). However, keyword spotting (KWS), as one of the most common speech recognition tasks, almost only benefits from frame-level deep learning due to the difficulty of getting competing sequence hypotheses. The few studies on sequence discriminative training for KWS are limited for fixed voca…
In automatic speech recognition (ASR) research, discriminative criteria have achieved superior performance in DNN-HMM systems. Given this success, the adoption of discriminative criteria is promising to boost the performance of end-to-end (E2E) ASR systems. With this motivation, previous works have introduced the minimum Bayesian risk (MBR, one of the discriminative criteria) into E2E ASR systems. However, the effectiveness and efficiency of the MBR-based methods are compromised: the MBR criterion is only used in system training, which creates a mismatch between training and decoding; the on-t…
National University of Singapore（新加坡国立大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired speech and text. In this paper, we take the idea of self-supervised pre-training one step further and propose token2vec, a novel joint pre-training framework for unpaired speech and text based on discrete representations of speech. Firstly, due to the distinct characteristics between speech and text modalities, where speech is continuous while text is discre…
The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text encoder for leveraging extensive text data and thus capture more context-aware linguistic information. However, this approach brings a mismatch problem between the speech encoder and the text encoder due to the different units used for modeling. In this paper, we propose an embedding aligner and modality switch training to better align the speech and text l…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）
Acoustic word embeddings --- fixed-dimensional vector representations of variable-length spoken word segments --- have begun to be considered for tasks such as speech recognition and query-by-example search. Such embeddings can be learned discriminatively so that they are similar for speech segments corresponding to the same word, while being dissimilar for segments corresponding to different words. Recent work has found that acoustic word embeddings can outperform dynamic time warping on query-by-example search and related word discrimination tasks. However, the space of embedding models and …
University of Electronic Science and Technology of China（电子科技大学）
Existing person re-identification has achieved great progress in the visible domain, capturing all the person images with visible cameras. However, in a 24-hour intelligent surveillance system, the visible cameras may be noneffective at night. In this situation, thermal cameras are the best supplemental components, which capture images without depending on visible light. Therefore, in this paper, we investigate the visible-thermal cross-modality person re-identification (VT Re-ID) problem. In VT Re-ID, there are two knotty problems should be well handled, cross-modality discrepancy and intra-m…
University of Electronic Science and Technology of China（电子科技大学）
Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which train the two-stream model in a separate way. However, it's hard to ensure discriminability and explore complementary information between different streams in existing works. In this work, we propose a novel cooperative cross-stream network that investigates the conjoint information in multiple different modalities. The jointly spatial and temporal stream networks feature extraction is accomplished by an end-to-end …
While deep learning methods have shown great success in medical image analysis, they require a number of medical images to train. Due to data privacy concerns and unavailability of medical annotators, it is oftentimes very difficult to obtain a lot of labeled medical images for model training. In this paper, we study cross-modality data augmentation to mitigate the data deficiency issue in the medical imaging domain. We propose a discriminative unpaired image-to-image translation model which translates images in source modality into images in target modality where the translation task is condu…
Multi-media communications facilitate global interaction among people. However, despite researchers exploring cross-lingual translation techniques such as machine translation and audio speech translation to overcome language barriers, there is still a shortage of cross-lingual studies on visual speech. This lack of research is mainly due to the absence of datasets containing visual speech and translated text pairs. In this paper, we present \textbf{AVMuST-TED}, the first dataset for \textbf{A}udio-\textbf{V}isual \textbf{Mu}ltilingual \textbf{S}peech \textbf{T}ranslation, derived from \textbf{…
In this work, we propose to utilize Convolutional Neural Networks to boost the performance of depth-induced salient object detection by capturing the high-level representative features for depth modality. We formulate the depth-induced saliency detection as a CNN-based cross-modal transfer problem to bridge the gap between the "data-hungry" nature of CNNs and the unavailability of sufficient labeled training data in depth modality. In the proposed approach, we leverage the auxiliary data from the source modality effectively by training the RGB saliency detection network to obtain the task-spec…
Tianjin University（天津大学）；National Institute of Informatics（国立信息学研究所）
Visual speech (i.e., lip motion) is highly related to auditory speech due to the co-occurrence and synchronization in speech production. This paper investigates this correlation and proposes a cross-modal speech co-learning paradigm. The primary motivation of our cross-modal co-learning method is modeling one modality aided by exploiting knowledge from another modality. Specifically, two cross-modal boosters are introduced based on an audio-visual pseudo-siamese structure to learn the modality-transformed correlation. Inside each booster, a max-feature-map embedded Transformer variant is propo…
In this paper, we introduce a novel audio-visual multi-modal bridging framework that can utilize both audio and visual information, even with uni-modal inputs. We exploit a memory network that stores source (i.e., visual) and target (i.e., audio) modal representations, where source modal representation is what we are given, and target modal representations are what we want to obtain from the memory network. We then construct an associative bridge between source and target memories that considers the interrelationship between the two memories. By learning the interrelationship through the assoc…
In this paper, we explore the unsupervised learning of a semantic embedding space for co-occurring sensory inputs. Specifically, we focus on the task of learning a semantic vector space for both spoken and handwritten digits using the TIDIGITs and MNIST datasets. Current techniques encode image and audio/textual inputs directly to semantic embeddings. In contrast, our technique maps an input to the mean and log variance vectors of a diagonal Gaussian from which sample semantic embeddings are drawn. In addition to encouraging semantic similarity between co-occurring inputs,our loss function inc…
DAE-Fuse: An Adaptive Discriminative Autoencoder for Multi-Modality Image Fusion
Department of Computer Science（计算机科学系）；Guangdong Provincial Key Lab of Interdisciplinary Research and Application for Data Science（广东省交叉学科研究与数据科学应用重点实验室）；Beijing Normal - Hong Kong Baptist University（北京师范大学-香港 Baptist大学）
Deep generative models have led to significant advances in cross-modal generation such as text-to-image synthesis. Training these models typically requires paired data with direct correspondence between modalities. We introduce the novel problem of translating instances from one modality to another without paired data by leveraging an intermediate modality shared by the two other modalities. To demonstrate this, we take the problem of translating images to speech. In this case, one could leverage disjoint datasets with one shared modality, e.g., image-text pairs and text-speech pairs, with tex…
Sun Yat-sen University（中山大学）；nii.ac.jp（日本国立信息学研究所）
This paper pays close attention to the cross-modality visible-infrared person re-identification (VI Re-ID) task, which aims to match pedestrian samples between visible and infrared modes. In order to reduce the modality-discrepancy between samples from different cameras, most existing works usually use constraints based on Euclidean metric. Because of the Euclidean based distance metric strategy cannot effectively measure the internal angles between the embedded vectors, the existing solutions cannot learn the angularly discriminative feature embedding. Since the most important factor affectin…
Due to the large cross-modality discrepancy between 2D sketches and 3D shapes, retrieving 3D shapes by sketches is a significantly challenging task. To address this problem, we propose a novel framework to learn a discriminative deep cross-modality adaptation model in this paper. Specifically, we first separately adopt two metric networks, following two deep convolutional neural networks (CNNs), to learn modality-specific discriminative features based on an importance-aware metric learning method. Subsequently, we explicitly introduce a cross-modality transformation network to compensate for t…
The measure between heterogeneous data is still an open problem. Many research works have been developed to learn a common subspace where the similarity between different modalities can be calculated directly. However, most of existing works focus on learning a latent subspace but the semantically structural information is not well preserved. Thus, these approaches cannot get desired results. In this paper, we propose a novel framework, termed Cross-modal subspace learning via Kernel correlation maximization and Discriminative structure-preserving (CKD), to solve this problem in two aspects. F…
Institute of Computer Science and Technology, Peking University（北京大学计算机科学技术研究所）
It is known that the inconsistent distribution and representation of different modalities, such as image and text, cause the heterogeneity gap that makes it challenging to correlate such heterogeneous data. Generative adversarial networks (GANs) have shown its strong ability of modeling data distribution and learning discriminative representation, existing GANs-based works mainly focus on generative problem to generate new data. We have different goal, aim to correlate heterogeneous data, by utilizing the power of GANs to model cross-modal joint distribution. Thus, we propose Cross-modal GANs …
Visible-infrared person re-identification (VI-ReID) is a task of matching the same individuals across the visible and infrared modalities. Its main challenge lies in the modality gap caused by cameras operating on different spectra. Existing VI-ReID methods mainly focus on learning general features across modalities, often at the expense of feature discriminability. To address this issue, we present a novel cycle-construction-based network for neutral yet discriminative feature learning, termed CycleTrans. Specifically, CycleTrans uses a lightweight Knowledge Capturing Module (KCM) to capture …
Istituto Italiano di Tecnologia（意大利技术研究院）；University of Genova（热那亚大学）；University of Verona（维罗纳大学）
Heterogeneous data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while training data can be accurately collected to include a variety of sensory modalities, it is often the case that not all of them are available in real life (testing) scenarios, where a model has to be deployed. This raises the challenge of how to extract information from multimodal data in the training stage, in a form that can be exploited at test time, considering limitations such as noisy or missing modalities. This paper presents a …
