Generative Adversarial Networks (GANs) for Audio-Visual Speech Recognition in Artificial Intelligence IoT

Audio-visual speech recognition (AVSR) is one of the most promising solutions for reliable speech recognition, particularly when audio is corrupted by noise. Additional visual information can be used for both automatic lip-reading and gesture recognition. Hand gestures are a form of non-verbal communication and can be used as a very important part of modern human–computer interaction systems. Currently, audio and video modalities are easily accessible by sensors of mobile devices. However, there is no out-of-the-box solution for automatic audio-visual speech and gesture recognition. This study introduces two deep neural network-based model architectures: one for AVSR and one for gesture recognition. The main novelty regarding audio-visual speech recognition lies in fine-tuning strategies for both visual and acoustic features and in the proposed end-to-end model, which considers three modality fusion approaches: prediction-level, feature-level, and model-level. The main novelty in gesture recognition lies in a unique set of spatio-temporal features, including those that consider lip articulation information. As there are no available datasets for the combined task, we evaluated our methods on two different large-scale corpora—LRW and AUTSL—and outperformed existing methods on both audio-visual speech recognition and gesture recognition tasks. We achieved AVSR accuracy for the LRW dataset equal to 98.76% and gesture recognition rate for the AUTSL dataset equal to 98.56%. The results obtained demonstrate not only the high performance of the proposed methodology, but also the fundamental possibility of recognizing audio-visual speech and gestures by sensors of mobile devices.

HMM-based audio-visual speech recognition (AVSR) systems have shown success in continuous speech recognition by combining visual and audio information, especially in noisy environments. In this paper we study how to improve decision trees used to create context classes in HMM-based AVSR systems. Traditionally, visual models have been trained with the same context classes as the audio only models. In this paper we investigate the use of separate decision trees to model the context classes for the audio and visual streams independently. Additionally we investigate the use of viseme classes in the decision tree building for the visual stream. On experiments with a 37-speaker 1.5 hours test set (about 12000 words) of continuous digits in noise, we obtain about a 3% absolute (20% relative) gain on AVSR performance by using separate decision trees for the audio and visual streams when using viseme classes in decision tree building for the visual stream.

The impact of automatic exaggeration of the visual articulatory features of a talker on the intelligibility of spectrally distorted speech

Audio-visual speech recognition is a natural and robust approach to improving human-robot interaction in noisy environments. Although multi-stream Dynamic Bayesian Network and coupled HMM are widely used for audio-visual speech recognition, they fail to learn the shared features between modalities and ignore the dependency of features among the frames within each discrete state. In this paper, we propose a Deep Dynamic Bayesian Network (DDBN) to perform unsupervised extraction of spatial-temporal multimodal features from Tibetan audio-visual speech data and build an accurate audio-visual speech recognition model under a no frame-independency assumption. The experiment results on Tibetan speech data from some real-world environments showed the proposed DDBN outperforms the state-of-art methods in word recognition accuracy.

Audio–visual speech recognition based on regulated transformer and spatio–temporal fusion strategy for driver assistive systems

Due to the high acoustic variability, children speech recognition suffers significant performance reduction on most ASR systems which are optimized mainly using adults speech with limited or even none children speech. One of the most straight ideas to solve this problem is to increase the children's speech data during training, however, it is restricted by the more difficult process and higher cost when collecting children's speech compared to adults'. In this work, we develop a generative adversarial network (GANs) based data augmentation method to increase the size of children's training data to improve speech recognition performance for children's speech. Two different types of GANs are explored under WGAN-GP training framework, including the unconditional GANs with an unsupervised learning framework and the conditional GANs using acoustic states as conditions. The proposed data augmentation approaches are evaluated on a Mandarin speech recognition task, with only 40-hour children speech or further including 100-hour adult speech in the training. The results show that more than relative 20% WER reduction can be obtained on children speech testset with the proposed method, and the generated children speech with GAN even can improve the adults' speech within our experimental setups.

The fusion of Internet of Intelligent Things (IoIT) in remote diagnosis of obstructive Sleep Apnea: A survey and a new model

Audio-visual speech recognition based on joint training with audio-visual speech enhancement for robust speech recognition

Multimodal feature extraction and fusion for audio-visual speech recognition

Human computer interaction (HCI) is very crucial in our day-to-day activity. Speech is one of the essential and intuitive ways to interact with machines such as Smartphone, which has multiple sensors as microphone, camera, etc. An efficient performance speech recognition system improves interaction between man and machines by making latter more receptive to user needs. Such system has Automatic speech recognition (ASR) engine, which is facing a unique challenge of accuracy in recognition rate. By integrating acoustic signal feature vectors with the visual features, a more robust audiovisual speech recognition engine (AVSR) could be developed for real environmental scenarios. This paper presents past research and development in the field of ASR and AVSR technologies. It describes key technological perspective and admiration of the fundamental progress in ASR and AVSR. The objective of this review is to summarize and compare some of the well-known methods experimented by previous researchers, and to conclude with direction on future research proficiency in HCI system using ASR and AVSR engine.

With the acceleration of economic development, enterprise management is facing more severe challenges. Big data analysis based on the intelligent Internet of Things (IoT) has a positive effect on the development of enterprise management and can make up for the shortcomings of enterprise management. In this paper, we develop a big data processing method based on intelligent IoT which can mine the factors that affect the company’s market sales from the collected data. Then, we propose a KNN classification algorithm based on overlapping k‐means clustering. This algorithm adds a training process to the traditional KNN algorithm, which can accurately classify data and greatly improve the efficiency of the classification algorithm. Numerical analysis results prove the effectiveness of the proposed algorithm.

Audio-Visual Speech Recognition (AVSR) has been studied for a long time in the literature. By leveraging the complementary information from both acoustic and visual modalities, this approach offers a promising solution for robust speech transcription. While recent AVSR models have achieved impressive performance on large-scale, uniformly distributed datasets, they often overlook the challenges posed by real-world scenarios-where data is collected across multiple sessions and environments, leading to significant domain shifts and heterogeneous distributions. Such heterogeneity can result in catastrophic forgetting and hinder the generalization ability of the conventional models. To bridge this gap, we introduce the Continual Audio-Visual Speech Recognition (CL-AVSR) problem, which formulates AVSR as a continual learning task. We establish a dedicated benchmark for CL-AVSR by designing three experimental scenarios that reflect real-world challenges: introducing varying background noise for the audio stream, degrading video quality for the visual stream, and dividing tasks by speaker characteristics to jointly affect both modalities. These scenarios systematically evaluate the model's ability to adapt and retain knowledge across dynamic and non-stationary data streams. To address the unique challenges of CL-AVSR, we propose the Interaction-enhanced Multimodal Prompt learning (IMP) framework. IMP builds upon a pre-trained AV-HuBERT backbone and integrates task-relevant soft prompts with cross-modal and cross-task interactions, enabling efficient knowledge transfer from high-quality source domains to typical low-quality target domains with minimal parameter overhead. The interactive prompts facilitate fine-grained alignment and adaptation between modalities and tasks, while contrastive regularization further mitigates catastrophic forgetting. Furthermore, we devise a multi-modal prompt selection strategy that leverages clustering-based feature analysis, empowering the model to dynamically select optimal prompts for unseen data distributions during inference. Extensive experiments on the LRS2 dataset demonstrate that IMP achieves substantial improvements over strong baselines, setting new state-of-the-art performance in all CL-AVSR scenarios. Our results highlight the effectiveness of IMP in enhancing continual learning capabilities for AVSR, paving the way for more robust and adaptable multi-modal speech recognition systems in real-world applications.

We describe an audio-visual automatic continuous speech recognition system, which significantly improves speech recognition performance over a wide range of acoustic noise levels, as well as under clean audio conditions. The system utilizes facial animation parameters (FAPs) supported by the MPEG-4 standard for the visual representation of speech. We also describe a robust and automatic algorithm we have developed to extract FAPs from visual data, which does not require hand labeling or extensive training procedures. The principal component analysis (PCA) was performed on the FAPs in order to decrease the dimensionality of the visual feature vectors, and the derived projection weights were used as visual features in the audio-visual automatic speech recognition (ASR) experiments. Both single-stream and multistream hidden Markov models (HMMs) were used to model the ASR system, integrate audio and visual information, and perform a relatively large vocabulary (approximately 1000 words) speech recognition experiments. The experiments performed use clean audio data and audio data corrupted by stationary white Gaussian noise at various SNRs. The proposed system reduces the word error rate (WER) by 20% to 23% relatively to audio-only speech recognition WERs, at various SNRs (0–30 dB) with additive white Gaussian noise, and by 19% relatively to audio-only speech recognition WER under clean audio conditions.

There has been a long term interest in using visual information to improve automatic speech recognition (ASR) system performance. Both audio and visual information are required in conventional audio visual speech recognition (AVSR) systems. This limits their wider applications when visual modality is not present. To this end, one possible solution is to use acoustic-to-visual (A2V) inversion techniques to generate visual features. Previous research in this direction used synthetic acoustic-articulatory parallel data in inversion model training. The acoustic mismatch between the audio-visual (AV) parallel data and target data was not considered. In addition, the target language to apply these technologies has been focused on English. In this article, a real 3D Audio-Visual Mandarin Continuous Speech (3DAV-MCS) corpus was used to train deep neural network based A2V inversion models. Cross-domain adaptation of the inversion models allows suitable visual features to be generated from acoustic data of mismatched domains. The proposed cross-domain deep visual feature generation techniques were evaluated on two state-of-the-art Mandarin speech recognition tasks: DAPRA GALE broadcast transcription and BOLT conversational telephone speech recognition. The AVSR systems constructed using the cross-domain generated visual features consistently outperformed the baseline convolutional neural network (CNN) ASR systems by up to 3.3% absolute (9.1% relative) character error rate (CER) reductions after both speaker adaptive training and sequence discriminative training were performed.

The climbing in population displacement in urban sectors has accelerated the adaptation of smart city policies across developing regions. Utilization of clean and sustainable energy is of utmost importance such as the demands of the entities can be met without any resource constraints. The management of energy in terms of electricity is therefore crucial to human livelihood. However, the present management process has flaws, leads to inefficiencies, and fraudulent activities, which further result in economic loss and resource wastage. To address such issues, this chapter proposes an intelligent Internet of Things (IoT) framework that uses tools like microcontrollers and sensors to minimize the need for human involvement, enhancing the system’s transparency and reliability. With such a consumer-friendly and secure system, live meter readings, automatic power cuts, and the detection of power theft, accidental situations can be performed effectively. The absence of wiring not only reduces installation costs but also minimizes the likelihood of faults. The integration of technologies such as IoT and artificial intelligence (AI) further improves reliability and consumer service. This proposed system can be a real game-changer that minimizes the involvement of intermediaries, promoting transparency and streamlining electricity management.