ترغب بنشر مسار تعليمي؟ اضغط هنا

Large-vocabulary Audio-visual Speech Recognition in Noisy Environments

149   0   0.0 ( 0 )
 نشر من قبل Wentao Yu
 تاريخ النشر 2021
والبحث باللغة English




اسأل ChatGPT حول البحث

Audio-visual speech recognition (AVSR) can effectively and significantly improve the recognition rates of small-vocabulary systems, compared to their audio-only counterparts. For large-vocabulary systems, however, there are still many difficulties, such as unsatisfactory video recognition accuracies, that make it hard to improve over audio-only baselines. In this paper, we specifically consider such scenarios, focusing on the large-vocabulary task of the LRS2 database, where audio-only performance is far superior to video-only accuracies, making this an interesting and challenging setup for multi-modal integration. To address the inherent difficulties, we propose a new fusion strategy: a recurrent integration network is trained to fuse the state posteriors of multiple single-modality models, guided by a set of model-based and signal-based stream reliability measures. During decoding, this network is used for stream integration within a hybrid recognizer, where it can thus cope with the time-variant reliability and information content of its multiple feature inputs. We compare the results with end-to-end AVSR systems as well as with competitive hybrid baseline models, finding that the new fusion strategy shows superior results, on average even outperforming oracle dynamic stream weighting, which has so far marked the -- realistically unachievable -- upper bound for standard stream weighting. Even though the pure lipreading performance is low, audio-visual integration is helpful under all -- clean, noisy, and reverberant -- conditions. On average, the new system achieves a relative word error rate reduction of 42.18% compared to the audio-only model, pointing at a high effectiveness of the proposed integration approach.



قيم البحث

اقرأ أيضاً

End-to-end acoustic speech recognition has quickly gained widespread popularity and shows promising results in many studies. Specifically the joint transformer/CTC model provides very good performance in many tasks. However, under noisy and distorted conditions, the performance still degrades notably. While audio-visual speech recognition can significantly improve the recognition rate of end-to-end models in such poor conditions, it is not obvious how to best utilize any available information on acoustic and visual signal quality and reliability in these models. We thus consider the question of how to optimally inform the transformer/CTC model of any time-variant reliability of the acoustic and visual information streams. We propose a new fusion strategy, incorporating reliability information in a decision fusion net that considers the temporal effects of the attention mechanism. This approach yields significant improvements compared to a state-of-the-art baseline model on the Lip Reading Sentences 2 and 3 (LRS2 and LRS3) corpus. On average, the new system achieves a relative word error rate reduction of 43% compared to the audio-only setup and 31% compared to the audiovisual end-to-end baseline.
Automatic audio-visual expression recognition can play an important role in communication services such as tele-health, VOIP calls and human-machine interaction. Accuracy of audio-visual expression recognition could benefit from the interplay between the two modalities. However, most audio-visual expression recognition systems, trained in ideal conditions, fail to generalize in real world scenarios where either the audio or visual modality could be missing due to a number of reasons such as limited bandwidth, interactors orientation, caller initiated muting. This paper studies the performance of a state-of-the art transformer when one of the modalities is missing. We conduct ablation studies to evaluate the model in the absence of either modality. Further, we propose a strategy to randomly ablate visual inputs during training at the clip or frame level to mimic real world scenarios. Results conducted on in-the-wild data, indicate significant generalization in proposed models trained on missing cues, with gains up to 17% for frame level ablations, showing that these training strategies cope better with the loss of input modalities.
Speech recognition in cocktail-party environments remains a significant challenge for state-of-the-art speech recognition systems, as it is extremely difficult to extract an acoustic signal of an individual speaker from a background of overlapping sp eech with similar frequency and temporal characteristics. We propose the use of speaker-targeted acoustic and audio-visual models for this task. We complement the acoustic features in a hybrid DNN-HMM model with information of the target speakers identity as well as visual features from the mouth region of the target speaker. Experimentation was performed using simulated cocktail-party data generated from the GRID audio-visual corpus by overlapping two speakerss speech on a single acoustic channel. Our audio-only baseline achieved a WER of 26.3%. The audio-visual model improved the WER to 4.4%. Introducing speaker identity information had an even more pronounced effect, improving the WER to 3.6%. Combining both approaches, however, did not significantly improve performance further. Our work demonstrates that speaker-targeted models can significantly improve the speech recognition in cocktail party environments.
118 - Jianwei Yu , Bo Wu , Rongzhi Gu 2020
Automatic speech recognition (ASR) of overlapped speech remains a highly challenging task to date. To this end, multi-channel microphone array data are widely used in state-of-the-art ASR systems. Motivated by the invariance of visual modality to aco ustic signal corruption, this paper presents an audio-visual multi-channel overlapped speech recognition system featuring tightly integrated separation front-end and recognition back-end. A series of audio-visual multi-channel speech separation front-end components based on textit{TF masking}, textit{filter&sum} and textit{mask-based MVDR} beamforming approaches were developed. To reduce the error cost mismatch between the separation and recognition components, they were jointly fine-tuned using the connectionist temporal classification (CTC) loss function, or a multi-task criterion interpolation with scale-invariant signal to noise ratio (Si-SNR) error cost. Experiments suggest that the proposed multi-channel AVSR system outperforms the baseline audio-only ASR system by up to 6.81% (26.83% relative) and 22.22% (56.87% relative) absolute word error rate (WER) reduction on overlapped speech constructed using either simulation or replaying of the lipreading sentence 2 (LRS2) dataset respectively.
Human speech processing is inherently multimodal, where visual cues (lip movements) help to better understand the speech in noise. Lip-reading driven speech enhancement significantly outperforms benchmark audio-only approaches at low signal-to-noise ratios (SNRs). However, at high SNRs or low levels of background noise, visual cues become fairly less effective for speech enhancement. Therefore, a more optimal, context-aware audio-visual (AV) system is required, that contextually utilises both visual and noisy audio features and effectively accounts for different noisy conditions. In this paper, we introduce a novel contextual AV switching component that contextually exploits AV cues with respect to different operating conditions to estimate clean audio, without requiring any SNR estimation. The switching module switches between visual-only (V-only), audio-only (A-only), and both AV cues at low, high and moderate SNR levels, respectively. The contextual AV switching component is developed by integrating a convolutional neural network and long-short-term memory network. For testing, the estimated clean audio features are utilised by the developed novel enhanced visually derived Wiener filter for clean audio power spectrum estimation. The contextual AV speech enhancement method is evaluated under real-world scenarios using benchmark Grid and ChiME3 corpora. For objective testing, perceptual evaluation of speech quality is used to evaluate the quality of the restored speech. For subjective testing, the standard mean-opinion-score method is used. The critical analysis and comparative study demonstrate the outperformance of proposed contextual AV approach, over A-only, V-only, spectral subtraction, and log-minimum mean square error based speech enhancement methods at both low and high SNRs, revealing its capability to tackle spectro-temporal variation in any real-world noisy condition.
التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا