Muqiao Yang

Muqiao Yang, Joseph Konan, David Bick et al. · cmu

While deep learning based speech enhancement systems have made rapid progress in improving the quality of speech signals, they can still produce outputs that contain artifacts and can sound unnatural. We propose a novel approach to speech enhancement aimed at improving perceptual quality and naturalness of enhanced signals by optimizing for key characteristics of speech. We first identify key acoustic parameters that have been found to correlate well with voice quality (e.g. jitter, shimmer, and spectral flux) and then propose objective functions which are aimed at reducing the difference between clean speech and enhanced speech with respect to these features. The full set of acoustic features is the extended Geneva Acoustic Parameter Set (eGeMAPS), which includes 25 different attributes associated with perception of speech. Given the non-differentiable nature of these feature computation, we first build differentiable estimators of the eGeMAPS and then use them to fine-tune existing speech enhancement systems. Our approach is generic and can be applied to any existing deep learning based enhancement systems to further improve the enhanced speech signals. Experimental results conducted on the Deep Noise Suppression (DNS) Challenge dataset shows that our approach can improve the state-of-the-art deep learning based enhancement systems.

Yunyang Zeng, Joseph Konan, Shuo Han et al. · cmu

Speech enhancement models have greatly progressed in recent years, but still show limits in perceptual quality of their speech outputs. We propose an objective for perceptual quality based on temporal acoustic parameters. These are fundamental speech features that play an essential role in various applications, including speaker recognition and paralinguistic analysis. We provide a differentiable estimator for four categories of low-level acoustic descriptors involving: frequency-related parameters, energy or amplitude-related parameters, spectral balance parameters, and temporal features. Unlike prior work that looks at aggregated acoustic parameters or a few categories of acoustic parameters, our temporal acoustic parameter (TAP) loss enables auxiliary optimization and improvement of many fine-grain speech characteristics in enhancement workflows. We show that adding TAPLoss as an auxiliary objective in speech enhancement produces speech with improved perceptual quality and intelligibility. We use data from the Deep Noise Suppression 2020 Challenge to demonstrate that both time-domain models and time-frequency domain models can benefit from our method.

Muqiao Yang, Naoyuki Kanda, Xiaofei Wang et al. · cmu

Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including overlapping speech of multiple speakers. Due to the difficulty in acquiring real conversation data with high-quality human transcriptions, a naïve simulation of multi-talker speech by randomly mixing multiple utterances was conventionally used for model training. In this work, we propose an improved technique to simulate multi-talker overlapping speech with realistic speech overlaps, where an arbitrary pattern of speech overlaps is represented by a sequence of discrete tokens. With this representation, speech overlapping patterns can be learned from real conversations based on a statistical language model, such as N-gram, which can be then used to generate multi-talker speech for training. In our experiments, multi-talker ASR models trained with the proposed method show consistent improvement on the word error rates across multiple datasets.

Muqiao Yang, Joseph Konan, David Bick et al. · cmu

Despite rapid advancement in recent years, current speech enhancement models often produce speech that differs in perceptual quality from real clean speech. We propose a learning objective that formalizes differences in perceptual quality, by using domain knowledge of acoustic-phonetics. We identify temporal acoustic parameters -- such as spectral tilt, spectral flux, shimmer, etc. -- that are non-differentiable, and we develop a neural network estimator that can accurately predict their time-series values across an utterance. We also model phoneme-specific weights for each feature, as the acoustic parameters are known to show different behavior in different phonemes. We can add this criterion as an auxiliary loss to any model that produces speech, to optimize speech outputs to match the values of clean speech in these features. Experimentally we show that it improves speech enhancement workflows in both time-domain and time-frequency domain, as measured by standard evaluation metrics. We also provide an analysis of phoneme-dependent improvement on acoustic parameters, demonstrating the additional interpretability that our method provides. This analysis can suggest which features are currently the bottleneck for improvement.

Xiang Li, Yandong Wen, Muqiao Yang et al. · cmu

Previous works on voice-face matching and voice-guided face synthesis demonstrate strong correlations between voice and face, but mainly rely on coarse semantic cues such as gender, age, and emotion. In this paper, we aim to investigate the capability of reconstructing the 3D facial shape from voice from a geometry perspective without any semantic information. We propose a voice-anthropometric measurement (AM)-face paradigm, which identifies predictable facial AMs from the voice and uses them to guide 3D face reconstruction. By leveraging AMs as a proxy to link the voice and face geometry, we can eliminate the influence of unpredictable AMs and make the face geometry tractable. Our approach is evaluated on our proposed dataset with ground-truth 3D face scans and corresponding voice recordings, and we find significant correlations between voice and specific parts of the face geometry, such as the nasal cavity and cranium. Our work offers a new perspective on voice-face correlation and can serve as a good empirical study for anthropometry science.

Muqiao Yang, Ian Lane, Shinji Watanabe

Continual Learning, also known as Lifelong Learning, aims to continually learn from new data as it becomes available. While prior research on continual learning in automatic speech recognition has focused on the adaptation of models across multiple different speech recognition tasks, in this paper we propose an experimental setting for \textit{online continual learning} for automatic speech recognition of a single task. Specifically focusing on the case where additional training data for the same task becomes available incrementally over time, we demonstrate the effectiveness of performing incremental model updates to end-to-end speech recognition models with an online Gradient Episodic Memory (GEM) method. Moreover, we show that with online continual learning and a selective sampling strategy, we can maintain an accuracy that is similar to retraining a model from scratch while requiring significantly lower computation costs. We have also verified our method with self-supervised learning (SSL) features.

Muqiao Yang, Chunlei Zhang, Yong Xu et al. · cmu

Speech enhancement aims to improve the quality of speech signals in terms of quality and intelligibility, and speech editing refers to the process of editing the speech according to specific user needs. In this paper, we propose a Unified Speech Enhancement and Editing (uSee) model with conditional diffusion models to handle various tasks at the same time in a generative manner. Specifically, by providing multiple types of conditions including self-supervised learning embeddings and proper text prompts to the score-based diffusion model, we can enable controllable generation of the unified speech enhancement and editing model to perform corresponding actions on the source speech. Our experiments show that our proposed uSee model can achieve superior performance in both speech denoising and dereverberation compared to other related generative speech enhancement models, and can perform speech editing given desired environmental sound text description, signal-to-noise ratios (SNR), and room impulse responses (RIR). Demos of the generated speech are available at https://muqiaoy.github.io/usee.

Umberto Cappellazzo, Enrico Fini, Muqiao Yang et al. · cmu

Recently, neural networks have shown impressive progress across diverse fields, with speech processing being no exception. However, recent breakthroughs in this area require extensive offline training using large datasets and tremendous computing resources. Unfortunately, these models struggle to retain their previously acquired knowledge when learning new tasks continually, and retraining from scratch is almost always impractical. In this paper, we investigate the problem of learning sequence-to-sequence models for spoken language understanding in a class-incremental learning (CIL) setting and we propose COCONUT, a CIL method that relies on the combination of experience replay and contrastive learning. Through a modified version of the standard supervised contrastive loss applied only to the rehearsal samples, COCONUT preserves the learned representations by pulling closer samples from the same class and pushing away the others. Moreover, we leverage a multimodal contrastive loss that helps the model learn more discriminative representations of the new data by aligning audio and text features. We also investigate different contrastive designs to combine the strengths of the contrastive loss with teacher-student architectures used for distillation. Experiments on two established SLU datasets reveal the effectiveness of our proposed approach and significant improvements over the baselines. We also show that COCONUT can be combined with methods that operate on the decoder side of the model, resulting in further metrics improvements.

Xukun Zhou, Jiwei Li, Tianwei Zhang et al.

Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems. Existing backdoor attacking systems face two severe issues:firstly, most backdoor triggers follow a uniform and usually input-independent pattern, e.g., insertion of specific trigger words, synonym replacement. This significantly hinders the stealthiness of the attacking model, leading the trained backdoor model being easily identified as malicious by model probes. Secondly, trigger-inserted poisoned sentences are usually disfluent, ungrammatical, or even change the semantic meaning from the original sentence, making them being easily filtered in the pre-processing stage. To resolve these two issues, in this paper, we propose an input-unique backdoor attack(NURA), where we generate backdoor triggers unique to inputs. IDBA generates context-related triggers by continuing writing the input with a language model like GPT2. The generated sentence is used as the backdoor trigger. This strategy not only creates input-unique backdoor triggers, but also preserves the semantics of the original input, simultaneously resolving the two issues above. Experimental results show that the IDBA attack is effective for attack and difficult to defend: it achieves high attack success rate across all the widely applied benchmarks, while is immune to existing defending methods. In addition, it is able to generate fluent, grammatical, and diverse backdoor inputs, which can hardly be recognized through human inspection.

Muqiao Yang, Xiang Li, Umberto Cappellazzo et al. · cmu

Continual learning has emerged as an increasingly important challenge across various tasks, including Spoken Language Understanding (SLU). In SLU, its objective is to effectively handle the emergence of new concepts and evolving environments. The evaluation of continual learning algorithms typically involves assessing the model's stability, plasticity, and generalizability as fundamental aspects of standards. However, existing continual learning metrics primarily focus on only one or two of the properties. They neglect the overall performance across all tasks, and do not adequately disentangle the plasticity versus stability/generalizability trade-offs within the model. In this work, we propose an evaluation methodology that provides a unified evaluation on stability, plasticity, and generalizability in continual learning. By employing the proposed metric, we demonstrate how introducing various knowledge distillations can improve different aspects of these three properties of the SLU model. We further show that our proposed metric is more sensitive in capturing the impact of task ordering in continual learning, making it better suited for practical use-case scenarios.

Umberto Cappellazzo, Muqiao Yang, Daniele Falavigna et al.

The ability to learn new concepts sequentially is a major weakness for modern neural networks, which hinders their use in non-stationary environments. Their propensity to fit the current data distribution to the detriment of the past acquired knowledge leads to the catastrophic forgetting issue. In this work we tackle the problem of Spoken Language Understanding applied to a continual learning setting. We first define a class-incremental scenario for the SLURP dataset. Then, we propose three knowledge distillation (KD) approaches to mitigate forgetting for a sequence-to-sequence transformer model: the first KD method is applied to the encoder output (audio-KD), and the other two work on the decoder output, either directly on the token-level (tok-KD) or on the sequence-level (seq-KD) distributions. We show that the seq-KD substantially improves all the performance metrics, and its combination with the audio-KD further decreases the average WER and enhances the entity prediction metric.

Xingbo Wang, Jianben He, Zhihua Jin et al.

Multimodal sentiment analysis aims to recognize people's attitudes from multiple communication channels such as verbal content (i.e., text), voice, and facial expressions. It has become a vibrant and important research topic in natural language processing. Much research focuses on modeling the complex intra- and inter-modal interactions between different communication channels. However, current multimodal models with strong performance are often deep-learning-based techniques and work like black boxes. It is not clear how models utilize multimodal information for sentiment predictions. Despite recent advances in techniques for enhancing the explainability of machine learning models, they often target unimodal scenarios (e.g., images, sentences), and little research has been done on explaining multimodal models. In this paper, we present an interactive visual analytics system, M2Lens, to visualize and explain multimodal models for sentiment analysis. M2Lens provides explanations on intra- and inter-modal interactions at the global, subset, and local levels. Specifically, it summarizes the influence of three typical interaction types (i.e., dominance, complement, and conflict) on the model predictions. Moreover, M2Lens identifies frequent and influential multimodal features and supports the multi-faceted exploration of model behaviors from language, acoustic, and visual modalities. Through two case studies and expert interviews, we demonstrate our system can help users gain deep insights into the multimodal models for sentiment analysis.

Yihong Dong, Ying Peng, Muqiao Yang et al.

Deep neural networks have been shown as a class of useful tools for addressing signal recognition issues in recent years, especially for identifying the nonlinear feature structures of signals. However, this power of most deep learning techniques heavily relies on an abundant amount of training data, so the performance of classic neural nets decreases sharply when the number of training data samples is small or unseen data are presented in the testing phase. This calls for an advanced strategy, i.e., model-agnostic meta-learning (MAML), which is able to capture the invariant representation of the data samples or signals. In this paper, inspired by the special structure of the signal, i.e., real and imaginary parts consisted in practical time-series signals, we propose a Complex-valued Attentional MEta Learner (CAMEL) for the problem of few-shot signal recognition by leveraging attention and meta-learning in the complex domain. To the best of our knowledge, this is also the first complex-valued MAML that can find the first-order stationary points of general nonconvex problems with theoretical convergence guarantees. Extensive experiments results showcase the superiority of the proposed CAMEL compared with the state-of-the-art methods.

Yao-Hung Hubert Tsai, Martin Q. Ma, Muqiao Yang et al.

This paper introduces Relative Predictive Coding (RPC), a new contrastive representation learning objective that maintains a good balance among training stability, minibatch size sensitivity, and downstream task performance. The key to the success of RPC is two-fold. First, RPC introduces the relative parameters to regularize the objective for boundedness and low variance. Second, RPC contains no logarithm and exponential score functions, which are the main cause of training instability in prior contrastive objectives. We empirically verify the effectiveness of RPC on benchmark vision and speech self-supervised learning tasks. Lastly, we relate RPC with mutual information (MI) estimation, showing RPC can be used to estimate MI with low variance.

Qiqi Xiao, Jiaxu Zou, Muqiao Yang et al.

Diabetic Retinopathy (DR) is a leading cause of blindness in working age adults. DR lesions can be challenging to identify in fundus images, and automatic DR detection systems can offer strong clinical value. Of the publicly available labeled datasets for DR, the Indian Diabetic Retinopathy Image Dataset (IDRiD) presents retinal fundus images with pixel-level annotations of four distinct lesions: microaneurysms, hemorrhages, soft exudates and hard exudates. We utilize the HEDNet edge detector to solve a semantic segmentation task on this dataset, and then propose an end-to-end system for pixel-level segmentation of DR lesions by incorporating HEDNet into a Conditional Generative Adversarial Network (cGAN). We design a loss function that adds adversarial loss to segmentation loss. Our experiments show that the addition of the adversarial loss improves the lesion segmentation performance over the baseline.

Yao-Hung Hubert Tsai, Martin Q. Ma, Muqiao Yang et al.

The human language can be expressed through multiple sources of information known as modalities, including tones of voice, facial gestures, and spoken language. Recent multimodal learning with strong performances on human-centric tasks such as sentiment analysis and emotion recognition are often black-box, with very limited interpretability. In this paper we propose Multimodal Routing, which dynamically adjusts weights between input modalities and output representations differently for each input sample. Multimodal routing can identify relative importance of both individual modalities and cross-modality features. Moreover, the weight assignment by routing allows us to interpret modality-prediction relationships not only globally (i.e. general trends over the whole dataset), but also locally for each single input sample, meanwhile keeping competitive performance compared to state-of-the-art methods.

Muqiao Yang, Martin Q. Ma, Dongyu Li et al.

While deep learning has received a surge of interest in a variety of fields in recent years, major deep learning models barely use complex numbers. However, speech, signal and audio data are naturally complex-valued after Fourier Transform, and studies have shown a potentially richer representation of complex nets. In this paper, we propose a Complex Transformer, which incorporates the transformer model as a backbone for sequence modeling; we also develop attention and encoder-decoder network operating for complex input. The model achieves state-of-the-art performance on the MusicNet dataset and an In-phase Quadrature (IQ) signal dataset.