Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement
Georgia Institute of Technology（佐治亚理工学院）；IBM Research（IBM研究院）
Chao-Han Huck Yang, Jun Qi, Pin-Yu Chen, Xiaoli Ma, Chin-Hui Lee
备注：
The authors have revised some annotations in Table 4 to improve the clarity. The authors thank reading feedbacks from Jonathan Le Roux. The first draft was finished in August 2019. Accepted to IEEE ICASSP 2020
发表信息：
2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhance adversarial speech signals. Specifically, we evaluate the model performance by interpretable speech recognition metrics and discuss the model performance by the augmented adversarial training. Our experiments show that our proposed U-Net$_{At}$ improves the perceptual evaluation of speech quality (PESQ) from 1.13 to 2.78, speech transmission index (STI) from 0.65 to 0.75, short-term objective intelligibility (STOI) from 0.83 to 0.96 on the task of speech enhancement with adversarial speech examples. We conduct experiments on the automatic speech recognition (ASR) task with adversarial audio attacks. We find that (i) temporal features learned by the attention network are capable of enhancing the robustness of DNN based ASR models; (ii) the generalization power of DNN based ASR model could be enhanced by applying adversarial training with an additive adversarial data augmentation. The ASR metric on word-error-rates (WERs) shows that there is an absolute 2.22 $\%$ decrease under gradient-based perturbation, and an absolute 2.03 $\%$ decrease, under evolutionary-optimized perturbation, which suggests that our enhancement models with adversarial training can further secure a resilient ASR system.
Deep convolutional neural networks are being actively investigated in a wide range of speech and audio processing applications including speech recognition, audio event detection and computational paralinguistics, owing to their ability to reduce factors of variations, for learning from speech. However, studies have suggested to favor a certain type of convolutional operations when building a deep convolutional neural network for speech applications although there has been promising results using different types of convolutional operations. In this work, we study four types of convolutional op…
National Taiwan University（国立台湾大学）；The Chinese University of Hong Kong（香港中文大学）
Audio-visual active speaker detection (AVASD) is well-developed, and now is an indispensable front-end for several multi-modal applications. However, to the best of our knowledge, the adversarial robustness of AVASD models hasn't been investigated, not to mention the effective defense against such attacks. In this paper, we are the first to reveal the vulnerability of AVASD models under audio-only, visual-only, and audio-visual adversarial attacks through extensive experiments. What's more, we also propose a novel audio-visual interaction loss (AVIL) for making attackers difficult to find feas…
Carnegie Mellon University（卡内基梅隆大学）；Indian Institute of Technology Bombay（印度理工学院孟买分校）；Indian Institute of Science（印度科学学院）
The problem of automatic accent identification is important for several applications like speaker profiling and recognition as well as for improving speech recognition systems. The accented nature of speech can be primarily attributed to the influence of the speaker's native language on the given speech recording. In this paper, we propose a novel accent identification system whose training exploits speech in native languages along with the accented speech. Specifically, we develop a deep Siamese network-based model which learns the association between accented speech recordings and the native…
Emotion plays an essential role in human-to-human communication, enabling us to convey feelings such as happiness, frustration, and sincerity. While modern speech technologies rely heavily on speech recognition and natural language understanding for speech content understanding, the investigation of vocal expression is increasingly gaining attention. Key considerations for building robust emotion models include characterizing and improving the extent to which a model, given its training data distribution, is able to generalize to unseen data conditions. This work investigated a long-shot-term …
Southern University of Science and Technology（南方科技大学）；The Hong Kong Polytechnic University（香港理工大学）；Tongji University（同济大学）；Microsoft（微软）；Peng Cheng Laboratory（鹏城实验室）
Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text mod…
Recent developments using End-to-End Deep Learning models have been shown to have near or better performance than state of the art Recurrent Neural Networks (RNNs) on Automatic Speech Recognition tasks. These models tend to be lighter weight and require less training time than traditional RNN-based approaches. However, these models take frequentist approach to weight training. In theory, network weights are drawn from a latent, intractable probability distribution. We introduce BayesSpeech for end-to-end Automatic Speech Recognition. BayesSpeech is a Bayesian Transformer Network where these in…
Current approaches to speech emotion recognition focus on speech features that can capture the emotional content of a speech signal. Mel Frequency Cepstral Coefficients (MFCCs) are one of the most commonly used representations for audio speech recognition and classification. This paper proposes Gammatone Frequency Cepstral Coefficients (GFCCs) as a potentially better representation of speech signals for emotion recognition. The effectiveness of MFCC and GFCC representations are compared and evaluated over emotion and intensity classification tasks with fully connected and recurrent neural netw…
Attention is a very popular and effective mechanism in artificial neural network-based sequence-to-sequence models. In this survey paper, a comprehensive review of the different attention models used in developing automatic speech recognition systems is provided. The paper focuses on the development and evolution of attention models for offline and streaming speech recognition within recurrent neural network- and Transformer- based architectures.
Shanghai Jiao Tong University（上海交通大学）；University of Illinois at Urbana–Champaign（伊利诺伊大学厄巴纳-香槟分校）；IBM Research（IBM研究院）；UC, Berkeley（加州大学伯克利分校）
Recent studies have highlighted adversarial examples as a ubiquitous threat to different neural network models and many downstream applications. Nonetheless, as unique data properties have inspired distinct and powerful learning principles, this paper aims to explore their potentials towards mitigating adversarial inputs. In particular, our results reveal the importance of using the temporal dependency in audio data to gain discriminate power against adversarial examples. Tested on the automatic speech recognition (ASR) tasks and three recent audio adversarial attacks, we find that (i) input t…
We investigate the use of generative adversarial networks (GANs) in speech dereverberation for robust speech recognition. GANs have been recently studied for speech enhancement to remove additive noises, but there still lacks of a work to examine their ability in speech dereverberation and the advantages of using GANs have not been fully established. In this paper, we provide deep investigations in the use of GAN-based dereverberation front-end in ASR. First, we study the effectiveness of different dereverberation networks (the generator in GAN) and find that LSTM leads a significant improveme…
In this paper, a time delay neural network (TDNN) based acoustic model is proposed to implement a fast-converged acoustic modeling for Korean speech recognition. The TDNN has an advantage in fast-convergence where the amount of training data is limited, due to subsampling which excludes duplicated weights. The TDNN showed an absolute improvement of 2.12% in terms of character error rate compared to feed forward neural network (FFNN) based modelling for Korean speech corpora. The proposed model converged 1.67 times faster than a FFNN-based model did.
Despite the remarkable progress achieved on automatic speech recognition, recognizing far-field speeches mixed with various noise sources is still a challenging task. In this paper, we introduce novel student-teacher transfer learning, BridgeNet which can provide a solution to improve distant speech recognition. There are two key features in BridgeNet. First, BridgeNet extends traditional student-teacher frameworks by providing multiple hints from a teacher network. Hints are not limited to the soft labels from a teacher network. Teacher's intermediate feature representations can better guide …
Despite significant efforts over the last few years to build a robust automatic speech recognition (ASR) system for different acoustic settings, the performance of the current state-of-the-art technologies significantly degrades in noisy reverberant environments. Convolutional Neural Networks (CNNs) have been successfully used to achieve substantial improvements in many speech processing applications including distant speech recognition (DSR). However, standard CNN architectures were not efficient in capturing long-term speech dynamics, which are essential in the design of a robust DSR system.…
We investigate the effectiveness of generative adversarial networks (GANs) for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR) systems. Prior work demonstrates that GANs can effectively suppress additive noise in raw waveform speech signals, improving perceptual quality metrics; however this technique was not justified in the context of ASR. In this work, we conduct a detailed study to measure the effectiveness of GANs in enhancing speech contaminated by both additive and reverberant noise. Motivated by recent advances in image processing,…
College of Electrical Engineering and Computer Science, National Taiwan University（台湾大学电机资讯学院）
End-to-end speech recognition systems have achieved competitive results compared to traditional systems. However, the complex transformations involved between layers given highly variable acoustic signals are hard to analyze. In this paper, we present our ASR probing model, which synthesizes speech from hidden representations of end-to-end ASR to examine the information maintain after each layer calculation. Listening to the synthesized speech, we observe gradual removal of speaker variability and noise as the layer goes deeper, which aligns with the previous studies on how deep network functi…
Centre for Perceptual and Interactive Intelligence（感知与交互智能中心）；The Chinese University of Hong Kong（香港中文大学）
A leaderboard named Speech processing Universal PERformance Benchmark (SUPERB), which aims at benchmarking the performance of a shared self-supervised learning (SSL) speech model across various downstream speech tasks with minimal modification of architectures and small amount of data, has fueled the research for speech representation learning. The SUPERB demonstrates speech SSL upstream models improve the performance of various downstream tasks through just minimal adaptation. As the paradigm of the self-supervised learning upstream model followed by downstream tasks arouses more attention in…
Aalto University（阿尔托大学）；National Institute of Informatics（国立信息学研究所）；NTT Communication Science Laboratories, NTT Corporation（NTT公司NTT通信科学实验室）
This paper proposes a method for generating speech from filterbank mel frequency cepstral coefficients (MFCC), which are widely used in speech applications, such as ASR, but are generally considered unusable for speech synthesis. First, we predict fundamental frequency and voicing information from MFCCs with an autoregressive recurrent neural net. Second, the spectral envelope information contained in MFCCs is converted to all-pole filters, and a pitch-synchronous excitation model matched to these filters is trained. Finally, we introduce a generative adversarial network -based noise model to …
Voice Activity Detection (VAD) is not easy task when the input audio signal is noisy, and it is even more complicated when the input is not even an audio recording. This is the case with Silent Speech Interfaces (SSI) where we record the movement of the articulatory organs during speech, and we aim to reconstruct the speech signal from this recording. Our SSI system synthesizes speech from ultrasonic videos of the tongue movement, and the quality of the resulting speech signals are evaluated by metrics such as the mean squared error loss function of the underlying neural network and the Mel-Ce…
We present SpeechStew, a speech recognition model that is trained on a combination of various publicly available speech recognition datasets: AMI, Broadcast News, Common Voice, LibriSpeech, Switchboard/Fisher, Tedlium, and Wall Street Journal. SpeechStew simply mixes all of these datasets together, without any special re-weighting or re-balancing of the datasets. SpeechStew achieves SoTA or near SoTA results across a variety of tasks, without the use of an external language model. Our results include 9.0\% WER on AMI-IHM, 4.7\% WER on Switchboard, 8.3\% WER on CallHome, and 1.3\% on WSJ, which…
Institute of Digital Research and Innovation, CADT（柬埔寨数字技术学院数字研究与创新研究所）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工学院）
The transition angles are defined to describe the vowel-to-vowel transitions in the acoustic space of the Spectral Subband Centroids, and the findings show that they are similar among speakers and speaking rates. In this paper, we propose to investigate the usage of polar coordinates in favor of angles to describe a speech signal by characterizing its acoustic trajectory and using them in Automatic Speech Recognition. According to the experimental results evaluated on the BRAF100 dataset, the polar coordinates achieved significantly higher accuracy than the angles in the mixed and cross-gender…
Université de Sherbrooke（舍布鲁克大学）；Université du Québec à Chicoutimi（魁北克大学希库蒂米分校）；Graz University of Technology（格拉茨工业大学）
Source separation and speech recognition are very difficult in the context of noisy and corrupted speech. Most conventional techniques need huge databases to estimate speech (or noise) density probabilities to perform separation or recognition. We discuss the potential of perceptive speech analysis and processing in combination with biologically plausible neural network processors. We illustrate the potential of such non-linear processing of speech on a source separation system inspired by an Auditory Scene Analysis paradigm. We also discuss a potential application in speech recognition.
This paper presented our work on applying Recurrent Deep Stacking Networks (RDSNs) to Robust Automatic Speech Recognition (ASR) tasks. In the paper, we also proposed a more efficient yet comparable substitute to RDSN, Bi- Pass Stacking Network (BPSN). The main idea of these two models is to add phoneme-level information into acoustic models, transforming an acoustic model to the combination of an acoustic model and a phoneme-level N-gram model. Experiments showed that RDSN and BPsn can substantially improve the performances over conventional DNNs.
Audio and visual signals complement each other in human speech perception, so do they in speech recognition. The visual hint is less evident than the acoustic hint, but more robust in a complex acoustic environment, as far as speech perception is concerned. It remains a challenge how we effectively exploit the interaction between audio and visual signals for automatic speech recognition. There have been studies to exploit visual signals as redundant or complementary information to audio input in a synchronous manner. Human studies suggest that visual signal primes the listener in advance as to…
In this paper, various structures and methods of Deep Artificial Neural Networks (DNN) will be evaluated and compared for the purpose of continuous Persian speech recognition. One of the first models of neural networks used in speech recognition applications were fully connected Neural Networks (FCNNs) and, consequently, Deep Neural Networks (DNNs). Although these models have better performance compared to GMM / HMM models, they do not have the proper structure to model local speech information. Convolutional Neural Network (CNN) is a good option for modeling the local structure of biological …
The Bidirectional LSTM (BLSTM) RNN based speech synthesis system is among the best parametric Text-to-Speech (TTS) systems in terms of the naturalness of generated speech, especially the naturalness in prosody. However, the model complexity and inference cost of BLSTM prevents its usage in many runtime applications. Meanwhile, Deep Feed-forward Sequential Memory Networks (DFSMN) has shown its consistent out-performance over BLSTM in both word error rate (WER) and the runtime computation cost in speech recognition tasks. Since speech synthesis also requires to model long-term dependencies compa…
Discrimination loss vs. SRT: A model-based approach towards harmonizing speech test interpretations
Institut Pasteur（巴斯德研究所）；Université Paris Cité（巴黎城市大学）；Inserm（法国国家健康与医学研究院）；Institut de l’Audition（听觉研究所）；IHU reConnect（reConnect创新医院研究所）；Hannover Medical School（汉诺威医学院）；Carl von Ossietzky Universität Oldenburg（卡尔·冯·奥西茨基奥尔登堡大学）
Speech recognition is one of the key topics in artificial intelligence, as it is one of the most common forms of communication in humans. Researchers have developed many speech-controlled prosthetic hands in the past decades, utilizing conventional speech recognition systems that use a combination of neural network and hidden Markov model. Recent advancements in general-purpose graphics processing units (GPGPUs) enable intelligent devices to run deep neural networks in real-time. Thus, state-of-the-art speech recognition systems have rapidly shifted from the paradigm of composite subsystems op…
Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）
Transcribing voice communications in NASA's launch control center is important for information utilization. However, automatic speech recognition in this environment is particularly challenging due to the lack of training data, unfamiliar words in acronyms, multiple different speakers and accents, and conversational characteristics of speaking. We used bidirectional deep recurrent neural networks to train and test speech recognition performance. We showed that data augmentation and custom language models can improve speech recognition accuracy. Transcribing communications from the launch contr…
Singapore University of Technology and Design（新加坡科技设计大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）
Neural models are known to be over-parameterized, and recent work has shown that sparse text-to-speech (TTS) models can outperform dense models. Although a plethora of sparse methods has been proposed for other domains, such methods have rarely been applied in TTS. In this work, we seek to answer the question: what are the characteristics of selected sparse techniques on the performance and model complexity? We compare a Tacotron2 baseline and the results of applying five techniques. We then evaluate the performance via the factors of naturalness, intelligibility and prosody, while reporting m…
Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and content, lacking controllability on other prosody-related factors. State-of-the-art speech representation learning methods for more speechfactors are using primary disentangle algorithms such as random resampling and ad-hoc bottleneck layer size adjustment,which however is hard to ensure robust speech representationdisentanglement. To increase the robustness of hi…
More than half of the 7,000 languages in the world are in imminent danger of going extinct. Traditional methods of documenting language proceed by collecting audio data followed by manual annotation by trained linguists at different levels of granularity. This time consuming and painstaking process could benefit from machine learning. Many endangered languages do not have any orthographic form but usually have speakers that are bi-lingual and trained in a high resource language. It is relatively easy to obtain textual translations corresponding to speech. In this work, we provide a multimodal …
In this paper we propose Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis with control over speech variation and style transfer. Flowtron borrows insights from IAF and revamps Tacotron in order to provide high-quality and expressive mel-spectrogram synthesis. Flowtron is optimized by maximizing the likelihood of the training data, which makes training simple and stable. Flowtron learns an invertible mapping of data to a latent space that can be manipulated to control many aspects of speech synthesis (pitch, tone, speech rate, cadence, accent). Our mean opi…
1 Universitat Polit\`ecnica de Catalunya, Barcelona, Spain 2 Telef\'onica Research, Barcelona, Spain 3 Universidad de M\'alaga, M\'alaga, Spain
Most methods of voice restoration for patients suffering from aphonia either produce whispered or monotone speech. Apart from intelligibility, this type of speech lacks expressiveness and naturalness due to the absence of pitch (whispered speech) or artificial generation of it (monotone speech). Existing techniques to restore prosodic information typically combine a vocoder, which parameterises the speech signal, with machine learning techniques that predict prosodic information. In contrast, this paper describes an end-to-end neural approach for estimating a fully-voiced speech waveform from …
North Co., Ltd.（诺斯有限公司）；Institute of Information Science, Academia Sinica（中央研究院信息科学研究所）；Research Center for Information Technology Innovation, Academia Sinica（中央研究院信息科技创新研究中心）
Recording channel mismatch between training and testing conditions has been shown to be a serious problem for speech separation. This situation greatly reduces the separation performance, and cannot meet the requirement of daily use. In this study, inheriting the use of our previously constructed TAT-2mix corpus, we address the channel mismatch problem by proposing a channel-aware audio separation network (CasNet), a deep learning framework for end-to-end time-domain speech separation. CasNet is implemented on top of TasNet. Channel embedding (characterizing channel information in a mixture of…
In this paper, we investigate a deep learning approach for speech denoising through an efficient ensemble of specialist neural networks. By splitting up the speech denoising task into non-overlapping subproblems and introducing a classifier, we are able to improve denoising performance while also reducing computational complexity. More specifically, the proposed model incorporates a gating network which assigns noisy speech signals to an appropriate specialist network based on either speech degradation level or speaker gender. In our experiments, a baseline recurrent network is compared agains…
In this paper, we present a blockwise optimization method for masking-based networks (BLOOM-Net) for training scalable speech enhancement networks. Here, we design our network with a residual learning scheme and train the internal separator blocks sequentially to obtain a scalable masking-based deep neural network for speech enhancement. Its scalability lets it dynamically adjust the run-time complexity depending on the test time environment. To this end, we modularize our models in that they can flexibly accommodate varying needs for enhancement performance and constraints on the resources, i…
National Taiwan University（台湾大学）；Academia Sinica（中央研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）；City University of Hong Kong（香港城市大学）
Numerous compression and acceleration strategies have achieved outstanding results on classification tasks in various fields, such as computer vision and speech signal processing. Nevertheless, the same strategies have yielded ungratified performance on regression tasks because the nature between these and classification tasks differs. In this paper, a novel sign-exponent-only floating-point network (SEOFP-NET) technique is proposed to compress the model size and accelerate the inference time for speech enhancement, a regression task of speech signal processing. The proposed method compressed …
College of Computer Science, Inner Mongolian University（内蒙古大学计算机学院）；Kingsoft AI Laboratory（金山人工智能实验室）
In recent decades, neural network based methods have significantly improved the performace of speech enhancement. Most of them estimate time-frequency (T-F) representation of target speech directly or indirectly, then resynthesize waveform using the estimated T-F representation. In this work, we proposed the temporal convolutional recurrent network (TCRN), an end-to-end model that directly map noisy waveform to clean waveform. The TCRN, which is combined convolution and recurrent neural network, is able to efficiently and effectively leverage short-term ang long-term information. Futuremore, w…
National Taiwan University（台湾大学）；Academia Sinica（中央研究院）
The calculation of most objective speech intelligibility assessment metrics requires clean speech as a reference. Such a requirement may limit the applicability of these metrics in real-world scenarios. To overcome this limitation, we propose a deep learning-based non-intrusive speech intelligibility assessment model, namely STOI-Net. The input and output of STOI-Net are speech spectral features and predicted STOI scores, respectively. The model is formed by the combination of a convolutional neural network and bidirectional long short-term memory (CNN-BLSTM) architecture with a multiplicative…
Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better represent the scenarios where such systems are used. In this paper, we explore methods that enable supervised speech enhancement systems to train on real-world degraded speech data. Specifically, we propose a semi-supervised approach for speech enhancement in which we first train a modified vector-quantized variational autoencoder that solves a source separation task. We then us…
Utilizing a human-perception-related objective function to train a speech enhancement model has become a popular topic recently. The main reason is that the conventional mean squared error (MSE) loss cannot represent auditory perception well. One of the typical hu-man-perception-related metrics, which is the perceptual evaluation of speech quality (PESQ), has been proven to provide a high correlation to the quality scores rated by humans. Owing to its complex and non-differentiable properties, however, the PESQ function may not be used to optimize speech enhancement models directly. In this st…
Indian Institute of Technology Guwahati（印度理工学院瓜哈提分校）
Language identification (LID) has relevance in many speech processing applications. For the automatic recognition of code-switching speech, the conventional approaches often employ an LID system for detecting the languages present within an utterance. In the existing works, the LID on code-switching speech involves modelling of the underlying languages separately. In this work, we propose a joint modelling based LID system for code-switching speech. To achieve the same, an attention-based end-to-end (E2E) network has been explored. For the development and evaluation of the proposed approach, a…
Rutgers, the State University of New Jersey（罗格斯新泽西州立大学）
Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range temporal correlations across high-resolution waveforms. These models, however, are limited by memory-intensive dilated convolution and aliasing artifacts from upsampling. We introduce an end-to-end fully-recurrent hourglass-shaped neural network architecture with residual connections for waveform-based single-channel speech enhancement. Our model can efficiently …
