Convolution-Based Channel-Frequency Attention for Text-Independent Speaker Verification

Deep convolutional neural networks (CNNs) have been applied to extracting speaker embeddings with significant success in speaker verification. Incorporating the attention mechanism has shown to be effective in improving the model performance. This paper presents an efficient two-dimensional convolution-based attention module, namely C2D-Att. The interaction between the convolution channel and frequency is involved in the attention calculation by lightweight convolution layers. This requires only a small number of parameters. Fine-grained attention weights are produced to represent channel and frequency-specific information. The weights are imposed on the input features to improve the representation ability for speaker modeling. The C2D-Att is integrated into a modified version of ResNet for speaker embedding extraction. Experiments are conducted on VoxCeleb datasets. The results show that C2DAtt is effective in generating discriminative attention maps and outperforms other attention methods. The proposed model shows robust performance with different scales of model size and achieves state-of-the-art results.

iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre

The capability of generating speech with specific type of emotion is desired for many applications of human-computer interaction. Cross-speaker emotion transfer is a common approach to generating emotional speech when speech with emotion labels from target speakers is not available for model training. This paper presents a novel cross-speaker emotion transfer system, named iEmoTTS. The system is composed of an emotion encoder, a prosody predictor, and a timbre encoder. The emotion encoder extracts the identity of emotion type as well as the respective emotion intensity from the mel-spectrogram of input speech. The emotion intensity is measured by the posterior probability that the input utterance carries that emotion. The prosody predictor is used to provide prosodic features for emotion transfer. The timber encoder provides timbre-related information for the system. Unlike many other studies which focus on disentangling speaker and style factors of speech, the iEmoTTS is designed to achieve cross-speaker emotion transfer via disentanglement between prosody and timbre. Prosody is considered as the main carrier of emotion-related speech characteristics and timbre accounts for the essential characteristics for speaker identification. Zero-shot emotion transfer, meaning that speech of target speakers are not seen in model training, is also realized with iEmoTTS. Extensive experiments of subjective evaluation have been carried out. The results demonstrate the effectiveness of iEmoTTS as compared with other recently proposed systems of cross-speaker emotion transfer. It is shown that iEmoTTS can produce speech with designated emotion type and controllable emotion intensity. With appropriate information bottleneck capacity, iEmoTTS is able to effectively transfer emotion information to a new speaker. Audio samples are publicly available\footnote{https://patrick-g-zhang.github.io/iemotts/}.

iExam: A Novel Online Exam Monitoring and Analysis System Based on Face Detection and Recognition

Online exams via video conference software like Zoom have been adopted in many schools due to COVID-19. While it is convenient, it is challenging for teachers to supervise online exams from simultaneously displayed student Zoom windows. In this paper, we propose iExam, an intelligent online exam monitoring and analysis system that can not only use face detection to assist invigilators in real-time student identification, but also be able to detect common abnormal behaviors (including face disappearing, rotating faces, and replacing with a different person during the exams) via a face recognition-based post-exam video analysis. To build such a novel system in its first kind, we overcome three challenges. First, we discover a lightweight approach to capturing exam video streams and analyzing them in real time. Second, we utilize the left-corner names that are displayed on each student's Zoom window and propose an improved OCR (optical character recognition) technique to automatically gather the ground truth for the student faces with dynamic positions. Third, we perform several experimental comparisons and optimizations to efficiently shorten the training and testing time required on teachers' PC. Our evaluation shows that iExam achieves high accuracy, 90.4% for real-time face detection and 98.4% for post-exam face recognition, while maintaining acceptable runtime performance. We have made iExam's source code available at https://github.com/VPRLab/iExam.

Transport-Oriented Feature Aggregation for Speaker Embedding Learning

Pooling is needed to aggregate frame-level features into utterance-level representations for speaker modeling. Given the success of statistics-based pooling methods, we hypothesize that speaker characteristics are well represented in the statistical distribution over the pre-aggregation layer's output, and propose to use transport-oriented feature aggregation for deriving speaker embeddings. The aggregated representation encodes the geometric structure of the underlying feature distribution, which is expected to contain valuable speaker-specific information that may not be represented by the commonly used statistical measures like mean and variance. The original transport-oriented feature aggregation is also extended to a weighted-frame version to incorporate the attention mechanism. Experiments on speaker verification with the Voxceleb dataset show improvement over statistics pooling and its attentive variant.

Learnable Frequency Filters for Speech Feature Extraction in Speaker Verification

Mel-scale spectrum features are used in various recognition and classification tasks on speech signals. There is no reason to expect that these features are optimal for all different tasks, including speaker verification (SV). This paper describes a learnable front-end feature extraction model. The model comprises a group of filters to transform the Fourier spectrum. Model parameters that define these filters are trained end-to-end and optimized specifically for the task of speaker verification. Compared to the standard Mel-scale filter-bank, the filters' bandwidths and center frequencies are adjustable. Experimental results show that applying the learnable acoustic front-end improves speaker verification performance over conventional Mel-scale spectrum features. Analysis on the learned filter parameters suggests that narrow-band information benefits the SV system performance. The proposed model achieves a good balance between performance and computation cost. In resource-constrained computation settings, the model significantly outperforms CNN-based learnable front-ends. The generalization ability of the proposed model is also demonstrated on different embedding extraction models and datasets.

EDITnet: A Lightweight Network for Unsupervised Domain Adaptation in Speaker Verification

Performance degradation caused by language mismatch is a common problem when applying a speaker verification system on speech data in different languages. This paper proposes a domain transfer network, named EDITnet, to alleviate the language-mismatch problem on speaker embeddings without requiring speaker labels. The network leverages a conditional variational auto-encoder to transfer embeddings from the target domain into the source domain. A self-supervised learning strategy is imposed on the transferred embeddings so as to increase the cosine distance between embeddings from different speakers. In the training process of the EDITnet, the embedding extraction model is fixed without fine-tuning, which renders the training efficient and low-cost. Experiments on Voxceleb and CN-Celeb show that the embeddings transferred by EDITnet outperform the un-transferred ones by around 30% with the ECAPA-TDNN512. Performance improvement can also be achieved with other embedding extraction models, e.g., TDNN, SE-ResNet34.

Multivariate Empirical Mode Decomposition of EEG for Mental State Detection at Localized Brain Lobes

In this study, the Multivariate Empirical Mode Decomposition (MEMD) approach is applied to extract features from multi-channel EEG signals for mental state classification. MEMD is a data-adaptive analysis approach which is suitable particularly for multi-dimensional non-linear signals like EEG. Applying MEMD results in a set of oscillatory modes called intrinsic mode functions (IMFs). As the decomposition process is data-dependent, the IMFs vary in accordance with signal variation caused by functional brain activity. Among the extracted IMFs, it is found that those corresponding to high-oscillation modes are most useful for detecting different mental states. Non-linear features are computed from the IMFs that contribute most to mental state detection. These MEMD features show a significant performance gain over the conventional tempo-spectral features obtained by Fourier transform and Wavelet transform. The dominance of specific brain region is observed by analysing the MEMD features extracted from associated EEG channels. The frontal region is found to be most significant with a classification accuracy of 98.06%. This multi-dimensional decomposition approach upholds joint channel properties and produces most discriminative features for EEG based mental state detection.

MEMD-HHT based Emotion Detection from EEG using 3D CNN

In this study, the Multivariate Empirical Mode Decomposition (MEMD) is applied to multichannel EEG to obtain scale-aligned intrinsic mode functions (IMFs) as input features for emotion detection. The IMFs capture local signal variation related to emotion changes. Among the extracted IMFs, the high oscillatory ones are found to be significant for the intended task. The Marginal Hilbert spectrum (MHS) is computed from the selected IMFs. A 3D convolutional neural network (CNN) is adopted to perform emotion detection with spatial-temporal-spectral feature representations that are constructed by stacking the multi-channel MHS over consecutive signal segments. The proposed approach is evaluated on the publicly available DEAP database. On binary classification of valence and arousal level (high versus low), the attained accuracies are 89.25% and 86.23% respectively, which significantly outperform previously reported systems with 2D CNN and/or conventional temporal and spectral features.

An Investigation on Applying Acoustic Feature Conversion to ASR of Adult and Child Speech

The performance of child speech recognition is generally less satisfactory compared to adult speech due to limited amount of training data. Significant performance degradation is expected when applying an automatic speech recognition (ASR) system trained on adult speech to child speech directly, as a result of domain mismatch. The present study is focused on adult-to-child acoustic feature conversion to alleviate this mismatch. Different acoustic feature conversion approaches, including deep neural network based and signal processing based, are investigated and compared under a fair experimental setting, in which converted acoustic features from the same amount of labeled adult speech are used to train the ASR models from scratch. Experimental results reveal that not all of the conversion methods lead to ASR performance gain. Specifically, as a classic unsupervised domain adaptation method, the statistic matching does not show an effectiveness. A disentanglement-based auto-encoder (DAE) conversion framework is found to be useful and the approach of F0 normalization achieves the best performance. It is noted that the F0 distribution of converted features is an important attribute to reflect the conversion quality, while utilizing an adult-child deep classification model to make judgment is shown to be inappropriate.

Unifying Cosine and PLDA Back-ends for Speaker Verification

State-of-art speaker verification (SV) systems use a back-end model to score the similarity of speaker embeddings extracted from a neural network model. The commonly used back-end models are the cosine scoring and the probabilistic linear discriminant analysis (PLDA) scoring. With the recently developed neural embeddings, the theoretically more appealing PLDA approach is found to have no advantage against or even be inferior the simple cosine scoring in terms of SV system performance. This paper presents an investigation on the relation between the two scoring approaches, aiming to explain the above counter-intuitive observation. It is shown that the cosine scoring is essentially a special case of PLDA scoring. In other words, by properly setting the parameters of PLDA, the two back-ends become equivalent. As a consequence, the cosine scoring not only inherits the basic assumptions for the PLDA but also introduces additional assumptions on the properties of input embeddings. Experiments show that the dimensional independence assumption required by the cosine scoring contributes most to the performance gap between the two methods under the domain-matched condition. When there is severe domain mismatch and the dimensional independence assumption does not hold, the PLDA would perform better than the cosine for domain adaptation.