We propose a quantum kernel learning (QKL) framework to address the inherent data sparsity issues often encountered in training large-scare acoustic models in low-resource scenarios. We project acoustic features based on classical-to-quantum feature encoding. Different from existing quantum convolution techniques, we utilize QKL with features in the quantum space to design kernel-based classifiers. Experimental results on challenging spoken command recognition tasks for a few low-resource languages, such as Arabic, Georgian, Chuvash, and Lithuanian, show that the proposed QKL-based hybrid approach attains good improvements over existing classical and quantum solutions.
In this paper, we propose a deep learning based multi-speaker direction of arrival (DOA) estimation with audio and visual signals by using permutation-free loss function. We first collect a data set for multi-modal sound source localization (SSL) where both audio and visual signals are recorded in real-life home TV scenarios. Then we propose a novel spatial annotation method to produce the ground truth of DOA for each speaker with the video data by transformation between camera coordinate and pixel coordinate according to the pin-hole camera model. With spatial location information served as another input along with acoustic feature, multi-speaker DOA estimation could be solved as a classification task of active speaker detection. Label permutation problem in multi-speaker related tasks will be addressed since the locations of each speaker are used as input. Experiments conducted on both simulated data and real data show that the proposed audio-visual DOA estimation model outperforms audio-only DOA estimation model by a large margin.
Differential privacy (DP) is one data protection avenue to safeguard user information used for training deep models by imposing noisy distortion on privacy data. Such a noise perturbation often results in a severe performance degradation in automatic speech recognition (ASR) in order to meet a privacy budget $\varepsilon$. Private aggregation of teacher ensemble (PATE) utilizes ensemble probabilities to improve ASR accuracy when dealing with the noise effects controlled by small values of $\varepsilon$. We extend PATE learning to work with dynamic patterns, namely speech utterances, and perform a first experimental demonstration that it prevents acoustic data leakage in ASR training. We evaluate three end-to-end deep models, including LAS, hybrid CTC/attention, and RNN transducer, on the open-source LibriSpeech and TIMIT corpora. PATE learning-enhanced ASR models outperform the benchmark DP-SGD mechanisms, especially under strict DP budgets, giving relative word error rate reductions between 26.2% and 27.5% for an RNN transducer model evaluated with LibriSpeech. We also introduce a DP-preserving ASR solution for pretraining on public speech corpora.
We propose an ensemble learning framework with Poisson sub-sampling to effectively train a collection of teacher models to issue some differential privacy (DP) guarantee for training data. Through boosting under DP, a student model derived from the training data suffers little model degradation from the models trained with no privacy protection. Our proposed solution leverages upon two mechanisms, namely: (i) a privacy budget amplification via Poisson sub-sampling to train a target prediction model that requires less noise to achieve a same level of privacy budget, and (ii) a combination of the sub-sampling technique and an ensemble teacher-student learning framework that introduces DP-preserving noise at the output of the teacher models and transfers DP-preserving properties via noisy labels. Privacy-preserving student models are then trained with the noisy labels to learn the knowledge with DP-protection from the teacher model ensemble. Experimental evidences on spoken command recognition and continuous speech recognition of Mandarin speech show that our proposed framework greatly outperforms existing DP-preserving algorithms in both speech processing tasks.
In this paper, we propose two techniques, namely joint modeling and data augmentation, to improve system performances for audio-visual scene classification (AVSC). We employ pre-trained networks trained only on image data sets to extract video embedding; whereas for audio embedding models, we decide to train them from scratch. We explore different neural network architectures for joint modeling to effectively combine the video and audio modalities. Moreover, data augmentation strategies are investigated to increase audio-visual training set size. For the video modality the effectiveness of several operations in RandAugment is verified. An audio-video joint mixup scheme is proposed to further improve AVSC performances. Evaluated on the development set of TAU Urban Audio Visual Scenes 2021, our final system can achieve the best accuracy of 94.2% among all single AVSC systems submitted to DCASE 2021 Task 1b.
Audio-only-based wake word spotting (WWS) is challenging under noisy conditions due to environmental interference in signal transmission. In this paper, we investigate on designing a compact audio-visual WWS system by utilizing visual information to alleviate the degradation. Specifically, in order to use visual information, we first encode the detected lips to fixed-size vectors with MobileNet and concatenate them with acoustic features followed by the fusion network for WWS. However, the audio-visual model based on neural networks requires a large footprint and a high computational complexity. To meet the application requirements, we introduce a neural network pruning strategy via the lottery ticket hypothesis in an iterative fine-tuning manner (LTH-IF), to the single-modal and multi-modal models, respectively. Tested on our in-house corpus for audio-visual WWS in a home TV scene, the proposed audio-visual system achieves significant performance improvements over the single-modality (audio-only or video-only) system under different noisy conditions. Moreover, LTH-IF pruning can largely reduce the network parameters and computations with no degradation of WWS performance, leading to a potential product solution for the TV wake-up scenario.
We propose two improvements to target-speaker voice activity detection (TS-VAD), the core component in our proposed speaker diarization system that was submitted to the 2022 Multi-Channel Multi-Party Meeting Transcription (M2MeT) challenge. These techniques are designed to handle multi-speaker conversations in real-world meeting scenarios with high speaker-overlap ratios and under heavy reverberant and noisy condition. First, for data preparation and augmentation in training TS-VAD models, speech data containing both real meetings and simulated indoor conversations are used. Second, in refining results obtained after TS-VAD based decoding, we perform a series of post-processing steps to improve the VAD results needed to reduce diarization error rates (DERs). Tested on the ALIMEETING corpus, the newly released Mandarin meeting dataset used in M2MeT, we demonstrate that our proposed system can decrease the DER by up to 66.55/60.59% relatively when compared with classical clustering based diarization on the Eval/Test set.
Multimodal emotion recognition is a challenging task in emotion computing as it is quite difficult to extract discriminative features to identify the subtle differences in human emotions with abstract concept and multiple expressions. Moreover, how to fully utilize both audio and visual information is still an open problem. In this paper, we propose a novel multimodal fusion attention network for audio-visual emotion recognition based on adaptive and multi-level factorized bilinear pooling (FBP). First, for the audio stream, a fully convolutional network (FCN) equipped with 1-D attention mechanism and local response normalization is designed for speech emotion recognition. Next, a global FBP (G-FBP) approach is presented to perform audio-visual information fusion by integrating selfattention based video stream with the proposed audio stream. To improve G-FBP, an adaptive strategy (AG-FBP) to dynamically calculate the fusion weight of two modalities is devised based on the emotion-related representation vectors from the attention mechanism of respective modalities. Finally, to fully utilize the local emotion information, adaptive and multi-level FBP (AMFBP) is introduced by combining both global-trunk and intratrunk data in one recording on top of AG-FBP. Tested on the IEMOCAP corpus for speech emotion recognition with only audio stream, the new FCN method outperforms the state-ofthe-art results with an accuracy of 71.40%. Moreover, validated on the AFEW database of EmotiW2019 sub-challenge and the IEMOCAP corpus for audio-visual emotion recognition, the proposed AM-FBP approach achieves the best accuracy of 63.09% and 75.49% respectively on the test set.