Today, many state-of-the-art automatic speech recognition (ASR) systems apply all-neural models that map audio to word sequences trained end-to-end along one global optimisation criterion in a fully data driven fashion. These models allow high precision ASR for domains and words represented in the training material but have difficulties recognising words that are rarely or not at all represented during training, i.e. trending words and new named entities. In this paper, we use a text-to-speech (TTS) engine to provide synthetic audio for out-of-vocabulary (OOV) words. We aim to boost the recognition accuracy of a recurrent neural network transducer (RNN-T) on OOV words by using the extra audio-text pairs, while maintaining the performance on the non-OOV words. Different regularisation techniques are explored and the best performance is achieved by fine-tuning the RNN-T on both original training data and extra synthetic data with elastic weight consolidation (EWC) applied on the encoder. This yields a 57% relative word error rate (WER) reduction on utterances containing OOV words without any degradation on the whole test set.
University Institute of Technology, University of Ngaoundere（恩冈代雷大学技术学院）；Faculty of Science, University of Ngaoundere（恩冈代雷大学理学院）；Rhodes University（罗兹大学）
Automatic Speech Recognition (ASR) is an active field of research due to its large number of applications and the proliferation of interfaces or computing devices that can support speech processing. However, the bulk of applications are based on well-resourced languages that overshadow under-resourced ones. Yet, ASR represents an undeniable means to promote such languages, especially when designing human-to-human or human-to-machine systems involving illiterate people. An approach to design an ASR system targeting under-resourced languages is to start with a limited vocabulary. ASR using a lim…
We present BERT-CTC-Transducer (BECTRA), a novel end-to-end automatic speech recognition (E2E-ASR) model formulated by the transducer with a BERT-enhanced encoder. Integrating a large-scale pre-trained language model (LM) into E2E-ASR has been actively studied, aiming to utilize versatile linguistic knowledge for generating accurate text. One crucial factor that makes this integration challenging lies in the vocabulary mismatch; the vocabulary constructed for a pre-trained LM is generally too large for E2E-ASR training and is likely to have a mismatch against a target ASR domain. To overcome s…
We present a training scheme for streaming automatic speech recognition (ASR) based on recurrent neural network transducers (RNN-T) which allows the encoder network to learn to exploit context audio from a stream, using segmented or partially labeled sequences of the stream during training. We show that the use of context audio during training and inference can lead to word error rate reductions of more than 6% in a realistic production setting for a voice assistant ASR system. We investigate the effect of the proposed training approach on acoustically challenging data containing background sp…
Recent advances in Automatic Speech Recognition (ASR) demonstrated how end-to-end systems are able to achieve state-of-the-art performance. There is a trend towards deeper neural networks, however those ASR models are also more complex and prone against specially crafted noisy data. Those Audio Adversarial Examples (AAE) were previously demonstrated on ASR systems that use Connectionist Temporal Classification (CTC), as well as attention-based encoder-decoder architectures. Following the idea of the hybrid CTC/attention ASR system, this work proposes algorithms to generate AAEs to combine both…
Detecting and recovering out-of-vocabulary (OOV) words is always challenging for Automatic Speech Recognition (ASR) systems. Many existing methods focus on modeling OOV words by modifying acoustic and language models and integrating context words cleverly into models. To train such complex models, we need a large amount of data with context words, additional training time, and increased model size. However, after getting the ASR transcription to recover context-based OOV words, the post-processing method has not been explored much. In this work, we propose a post-processing technique to improv…
Automatic speech recognition (ASR) systems are vulnerable to audio adversarial examples that attempt to deceive ASR systems by adding perturbations to benign speech signals. Although an adversarial example and the original benign wave are indistinguishable to humans, the former is transcribed as a malicious target sentence by ASR systems. Several methods have been proposed to generate audio adversarial examples and feed them directly into the ASR system (over-line). Furthermore, many researchers have demonstrated the feasibility of robust physical audio adversarial examples(over-air). To defen…
In a transfer-based attack against Automatic Speech Recognition (ASR) systems, attacks are unable to access the architecture and parameters of the target model. Existing attack methods are mostly investigated in voice assistant scenarios with restricted voice commands, prohibiting their applicability to more general ASR related applications. To tackle this challenge, we propose a novel contextualized attack with deletion, insertion, and substitution adversarial behaviors, namely TransAudio, which achieves arbitrary word-level attacks based on the proposed two-stage framework. To strengthen the…
Audiovisual automatic speech recognition (AV-ASR) aims to improve the robustness of a speech recognition system by incorporating visual information. Training fully supervised multimodal models for this task from scratch, however is limited by the need for large labelled audiovisual datasets (in each downstream domain of interest). We present AVFormer, a simple method for augmenting audio-only models with visual information, at the same time performing lightweight domain adaptation. We do this by (i) injecting visual embeddings into a frozen ASR model using lightweight trainable adaptors. We sh…
End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these models typically require more data to achieve comparable results. Well-known model adaptation techniques, to account for domain and style adaptation, are not easily applicable to end-to-end systems. Conventional HMM-based systems, on the other hand, have been optimized for various production environments and use cases. In this work, we propose to combine the …
Istituto Italiano di Tecnologia（意大利技术研究院）；University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）；University of Padova（帕多瓦大学）
In this paper, we analyzed how audio-visual speech enhancement can help to perform the ASR task in a cocktail party scenario. Therefore we considered two simple end-to-end LSTM-based models that perform single-channel audio-visual speech enhancement and phone recognition respectively. Then, we studied how the two models interact, and how to train them jointly affects the final result. We analyzed different training strategies that reveal some interesting and unexpected behaviors. The experiments show that during optimization of the ASR task the speech enhancement capability of the model signif…
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 mu…
Baidu Research USA（百度美国研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）
Much of the recent literature on automatic speech recognition (ASR) is taking an end-to-end approach. Unlike English where the writing system is closely related to sound, Chinese characters (Hanzi) represent meaning, not sound. We propose factoring audio -> Hanzi into two sub-tasks: (1) audio -> Pinyin and (2) Pinyin -> Hanzi, where Pinyin is a system of phonetic transcription of standard Chinese. Factoring the audio -> Hanzi task in this way achieves 3.9% CER (character error rate) on the Aishell-1 corpus, the best result reported on this dataset so far.
Despite improved performances of the latest Automatic Speech Recognition (ASR) systems, transcription errors are still unavoidable. These errors can have a considerable impact in critical domains such as healthcare, when used to help with clinical documentation. Therefore, detecting ASR errors is a critical first step in preventing further error propagation to downstream applications. To this end, we propose a novel end-to-end approach for ASR error detection using audio-transcript entailment. To the best of our knowledge, we are the first to frame this problem as an end-to-end entailment task…
Traditionally, audio-visual automatic speech recognition has been studied under the assumption that the speaking face on the visual signal is the face matching the audio. However, in a more realistic setting, when multiple faces are potentially on screen one needs to decide which face to feed to the A/V ASR system. The present work takes the recent progress of A/V ASR one step further and considers the scenario where multiple people are simultaneously on screen (multi-person A/V ASR). We propose a fully differentiable A/V ASR model that is able to handle multiple face tracks in a video. Instea…
There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems. These attacks pose new challenges to deep learning security and have raised significant concerns in deploying ASR systems in safety-critical applications. In this work, we introduce WaveGuard: a framework for detecting adversarial inputs that are crafted to attack ASR systems. Our framework incorporates audio transformation functions and analyses the ASR transcriptions of the original and transformed audio to detect adversarial inputs. We demonstrate that our defense framewor…
Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show that our defense is able to detect attacks created through optimized perturbations and frequency masking on a state-of-the-art end-to-end ASR system. Furthermore, the defense can be made robust against attacks that are immune to noise reduction. We test our defense on Mozilla's CommonVoice dataset, the UrbanSound dataset, and an excerpt of the LibriSpeech datas…
Audio-visual automatic speech recognition (AV-ASR) is an extension of ASR that incorporates visual cues, often from the movements of a speaker's mouth. Unlike works that simply focus on the lip motion, we investigate the contribution of entire visual frames (visual actions, objects, background etc.). This is particularly useful for unconstrained videos, where the speaker is not necessarily visible. To solve this task, we propose a new sequence-to-sequence AudioVisual ASR TrAnsformeR (AVATAR) which is trained end-to-end from spectrograms and full-frame RGB. To prevent the audio stream from domi…
Leveraging context information is an intuitive idea to improve performance on conversational automatic speech recognition(ASR). Previous works usually adopt recognized hypotheses of historical utterances as preceding context, which may bias the current recognized hypothesis due to the inevitable historicalrecognition errors. To avoid this problem, we propose an audio-textual cross-modal representation extractor to learn contextual representations directly from preceding speech. Specifically, it consists of two modal-related encoders, extracting high-level latent features from speech and the co…
Swinburne University of Technology（斯威本科技大学）；The University of Adelaide（阿德莱德大学）；Deakin University（迪肯大学）；The University of New South Wales（新南威尔士大学）；CSIRO-Data61（澳大利亚联邦科学与工业研究组织数据61所）；Macquarie University（麦考瑞大学）；James Cook University（詹姆斯库克大学）
With the rapid development of deep learning techniques, the popularity of voice services implemented on various Internet of Things (IoT) devices is ever increasing. In this paper, we examine user-level membership inference in the problem space of voice services, by designing an audio auditor to verify whether a specific user had unwillingly contributed audio used to train an automatic speech recognition (ASR) model under strict black-box access. With user representation of the input audio data and their corresponding translated text, our trained auditor is effective in user-level audit. We als…
Automatic Speech Recognition (ASR) systems convert speech into text and can be placed into two broad categories: traditional and fully end-to-end. Both types have been shown to be vulnerable to adversarial audio examples that sound benign to the human ear but force the ASR to produce malicious transcriptions. Of these attacks, only the "psychoacoustic" attacks can create examples with relatively imperceptible perturbations, as they leverage the knowledge of the human auditory system. Unfortunately, existing psychoacoustic attacks can only be applied against traditional models, and are obsolete…
In this study, we try to address the problem of leveraging visual signals to improve Automatic Speech Recognition (ASR), also known as visual context-aware ASR (VC-ASR). We explore novel VC-ASR approaches to leverage video and text representations extracted by a self-supervised pre-trained text-video embedding model. Firstly, we propose a multi-stream attention architecture to leverage signals from both audio and video modalities. This architecture consists of separate encoders for the two modalities and a single decoder that attends over them. We show that this architecture is better than fus…
Georgia Institute of Technology（佐治亚理工学院）；Apple（苹果公司）
In embedding-matching acoustic-to-word (A2W) ASR, every word in the vocabulary is represented by a fixed-dimension embedding vector that can be added or removed independently of the rest of the system. The approach is potentially an elegant solution for the dynamic out-of-vocabulary (OOV) words problem, where speaker- and context-dependent named entities like contact names must be incorporated into the ASR on-the-fly for every speech utterance at testing time. Challenges still remain, however, in improving the overall accuracy of embedding-matching A2W. In this paper, we contribute two methods…
Automatic speech recognition (ASR) models are prevalent, particularly in applications for voice navigation and voice control of domestic appliances. The computational core of ASRs are deep neural networks (DNNs) that have been shown to be susceptible to adversarial perturbations; easily misused by attackers to generate malicious outputs. To help test the security and robustnesss of ASRS, we propose techniques that generate blackbox (agnostic to the DNN), untargeted adversarial attacks that are portable across ASRs. This is in contrast to existing work that focuses on whitebox targeted attacks …
Audio is an important medium in people's daily life, hidden information can be embedded into audio for covert communication. Current audio information hiding techniques can be roughly classed into time domain-based and transform domain-based techniques. Time domain-based techniques have large hiding capacity but low imperceptibility. Transform domain-based techniques have better imperceptibility, but the hiding capacity is poor. This paper proposes a new audio information hiding technique which shows high hiding capacity and good imperceptibility. The proposed audio information hiding method t…
Accurate prediction of the user intent to interact with a voice assistant (VA) on a device (e.g. on the phone) is critical for achieving naturalistic, engaging, and privacy-centric interactions with the VA. To this end, we present a novel approach to predict the user's intent (the user speaking to the device or not) directly from acoustic and textual information encoded at subword tokens which are obtained via an end-to-end ASR model. Modeling directly the subword tokens, compared to modeling of the phonemes and/or full words, has at least two advantages: (i) it provides a unique vocabulary re…
Carnegie Mellon University（卡内基梅隆大学）；Sony Group Corporation（索尼集团公司）
Speech samples recorded in both indoor and outdoor environments are often contaminated with secondary audio sources. Most end-to-end monaural speech recognition systems either remove these background sounds using speech enhancement or train noise-robust models. For better model interpretability and holistic understanding, we aim to bring together the growing field of automated audio captioning (AAC) and the thoroughly studied automatic speech recognition (ASR). The goal of AAC is to generate natural language descriptions of contents in audio samples. We propose several approaches for end-to-en…
Spoken language understanding (SLU) systems translate voice input commands to semantics which are encoded as an intent and pairs of slot tags and values. Most current SLU systems deploy a cascade of two neural models where the first one maps the input audio to a transcript (ASR) and the second predicts the intent and slots from the transcript (NLU). In this paper, we introduce FANS, a new end-to-end SLU model that fuses an ASR audio encoder to a multi-task NLU decoder to infer the intent, slot tags, and slot values directly from a given input audio, obviating the need for transcription. FANS c…
We present ASR Bundestag, a dataset for automatic speech recognition in German, consisting of 610 hours of aligned audio-transcript pairs for supervised training as well as 1,038 hours of unlabeled audio snippets for self-supervised learning, based on raw audio data and transcriptions from plenary sessions and committee meetings of the German parliament. In addition, we discuss utilized approaches for the automated creation of speech datasets and assess the quality of the resulting dataset based on evaluations and finetuning of a pre-trained state of the art model. We make the dataset publicly…
University of Louisiana at Lafayette（路易斯安那大学拉斐特分校）
CAPTCHAs are designed to prevent malicious bot programs from abusing websites. Most online service providers deploy audio CAPTCHAs as an alternative to text and image CAPTCHAs for visually impaired users. However, prior research investigating the security of audio CAPTCHAs found them highly vulnerable to automated attacks using Automatic Speech Recognition (ASR) systems. To improve the robustness of audio CAPTCHAs against automated abuses, we present the design and implementation of an audio adversarial CAPTCHA (aaeCAPTCHA) system in this paper. The aaeCAPTCHA system exploits audio adversarial…
Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several unsupervised pre-training models have been proposed, applying such models directly might still be sub-optimal if more labeled, training data could be obtained without a large cost. In this paper, we present a weakly supervised framework for constructing ASR systems with massive video data. As videos often contain human-speech audios aligned with subtitles, w…
Due to the dynamic nature of human language, automatic speech recognition (ASR) systems need to continuously acquire new vocabulary. Out-Of-Vocabulary (OOV) words, such as trending words and new named entities, pose problems to modern ASR systems that require long training times to adapt their large numbers of parameters. Different from most previous research focusing on language model post-processing, we tackle this problem on an earlier processing level and eliminate the bias in acoustic modeling to recognize OOV words acoustically. We propose to generate OOV words using text-to-speech syste…
