We propose a unified framework for low resource automatic speech recognition tasks named meta audio concatenation (MAC). It is easy to implement and can be carried out in extremely low resource environments. Mathematically, we give a clear description of MAC framework from the perspective of bayesian sampling. In this framework, we leverage a novel concatenative synthesis text-to-speech system to boost the low resource ASR task. By the concatenative synthesis text-to-speech system, we can integrate language pronunciation rules and adjust the TTS process. Furthermore, we propose a broad notion of meta audio set to meet the modeling needs of different languages and different scenes when using the system. Extensive experiments have demonstrated the great effectiveness of MAC on low resource ASR tasks. For CTC greedy search, CTC prefix, attention, and attention rescoring decode mode in Cantonese ASR task, Taiwanese ASR task, and Japanese ASR task the MAC method can reduce the CER by more than 15\%. Furthermore, in the ASR task, MAC beats wav2vec2 (with fine-tuning) on common voice datasets of Cantonese and gets really competitive results on common voice datasets of Taiwanese and Japanese. Among them, it is worth mentioning that we achieve a \textbf{10.9\%} character error rate (CER) on the common voice Cantonese ASR task, bringing about \textbf{30\%} relative improvement compared to the wav2vec2 (with fine-tuning).
End-to-end speech recognition models trained using joint Connectionist Temporal Classification (CTC)-Attention loss have gained popularity recently. In these models, a non-autoregressive CTC decoder is often used at inference time due to its speed and simplicity. However, such models are hard to personalize because of their conditional independence assumption that prevents output tokens from previous time steps to influence future predictions. To tackle this, we propose a novel two-way approach that first biases the encoder with attention over a predefined list of rare long-tail and out-of-voc…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing Forestry University（北京林业大学）
In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) systems. To alleviate this issue, the commonest way is to use a well-designed speech enhancement approach as the front-end of ASR. However, more complex pipelines, more computations and even higher hardware costs (microphone array) are additionally consumed for this kind of methods. In addition, speech enhancement would result in speech distortions and mismatches to training. In this paper, we propose an adversarial traini…
Boosting Cross-Domain Speech Recognition with Self-Supervision
Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft STCA（微软（亚洲）互联网工程院）
Boosting keyword spotting through on-device learnable user speech characteristics
Integrated Systems Laboratory (IIS), ETH Zurich（苏黎世联邦理工学院集成系统实验室）；Zurich Research Center, Huawei Technologies（华为技术有限公司苏黎世研究中心）；DEI, University of Bologna（博洛尼亚大学电子、计算机与工程系）
Automatic Speech Recognition (ASR) systems frequently use a search-based decoding strategy aiming to find the best attainable transcript by considering multiple candidates. One prominent speech recognition decoding heuristic is beam search, which seeks the transcript with the greatest likelihood computed using the predicted distribution. While showing substantial performance gains in various tasks, beam search loses some of its effectiveness when the predicted probabilities are highly confident, i.e., the predicted distribution is massed for a single or very few classes. We show that recently …
Nara Institute of Science and Technology（奈良科学技术研究所）；RIKEN Center for Advanced Intelligence Project AIP（理化学研究所高级智能项目AIP中心）
Even though over seven hundred ethnic languages are spoken in Indonesia, the available technology remains limited that could support communication within indigenous communities as well as with people outside the villages. As a result, indigenous communities still face isolation due to cultural barriers; languages continue to disappear. To accelerate communication, speech-to-speech translation (S2ST) technology is one approach that can overcome language barriers. However, S2ST systems require machine translation (MT), speech recognition (ASR), and synthesis (TTS) that rely heavily on supervised…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN（理化学研究所）
Inspired by a human speech chain mechanism, a machine speech chain framework based on deep learning was recently proposed for the semi-supervised development of automatic speech recognition (ASR) and text-to-speech synthesis TTS) systems. However, the mechanism to listen while speaking can be done only after receiving entire input sequences. Thus, there is a significant delay when encountering long utterances. By contrast, humans can listen to what hey speak in real-time, and if there is a delay in hearing, they won't be able to continue speaking. In this work, we propose an incremental machin…
Automatic Speech Recognition (ASR), as the assistance of speech communication between pilots and air-traffic controllers, can significantly reduce the complexity of the task and increase the reliability of transmitted information. ASR application can lead to a lower number of incidents caused by misunderstanding and improve air traffic management (ATM) efficiency. Evidently, high accuracy predictions, especially, of key information, i.e., callsigns and commands, are required to minimize the risk of errors. We prove that combining the benefits of ASR and Natural Language Processing (NLP) method…
We present a method to remove unknown convolutive noise introduced to speech by reverberations of recording environments, utilizing some amount of training speech data from the reverberant environment, and any available non-reverberant speech data. Using Fourier transform computed over long temporal windows, which ideally cover the entire room impulse response, we convert room induced convolution to additions in the log spectral domain. Next, we compute a spectral normalization vector from statistics gathered over reverberated as well as over clean speech in the log spectral domain. During ope…
Southern University of Science and Technology（南方科技大学）；Microsoft China（微软中国）
Machine Speech Chain, which integrates both end-to-end (E2E) automatic speech recognition (ASR) and text-to-speech (TTS) into one circle for joint training, has been proven to be effective in data augmentation by leveraging large amounts of unpaired data. In this paper, we explore the TTS->ASR pipeline in speech chain to do domain adaptation for both neural TTS and E2E ASR models, with only text data from target domain. We conduct experiments by adapting from audiobook domain (LibriSpeech) to presentation domain (TED-LIUM), there is a relative word error rate (WER) reduction of 10% for the E2E…
Boosting the Transferability of Audio Adversarial Examples with Acoustic Representation Optimization
National Engineering Research Center of Disaster Backup and Recovery（国家防灾备份与恢复工程研究中心）；School of Cyberspace Security, Beijing University of Posts and Telecommunications（北京邮电大学网络空间安全学院）
Hohai University（河海大学）；RMIT University（皇家墨尔本理工大学）；National University of Singapore（新加坡国立大学）
Keyword spotting (KWS) has been widely used in various speech control scenarios. The training of KWS is usually based on deep neural networks and requires a large amount of data. Manufacturers often use third-party data to train KWS. However, deep neural networks are not sufficiently interpretable to manufacturers, and attackers can manipulate third-party training data to plant backdoors during the model training. An effective backdoor attack can force the model to make specified judgments under certain conditions, i.e., triggers. In this paper, we design a backdoor attack scheme based on Pitc…
Very deep CNNs achieve state-of-the-art results in both computer vision and speech recognition, but are difficult to train. The most popular way to train very deep CNNs is to use shortcut connections (SC) together with batch normalization (BN). Inspired by Self- Normalizing Neural Networks, we propose the self-normalizing deep CNN (SNDCNN) based acoustic model topology, by removing the SC/BN and replacing the typical RELU activations with scaled exponential linear unit (SELU) in ResNet-50. SELU activations make the network self-normalizing and remove the need for both shortcut connections and …
Recent studies have shown that using an external Language Model (LM) benefits the end-to-end Automatic Speech Recognition (ASR). However, predicting tokens that appear less frequently in the training set is still quite challenging. The long-tail prediction problems have been widely studied in many applications, but only been addressed by a few studies for ASR and LMs. In this paper, we propose a new memory augmented lookup dictionary based Transformer architecture for LM. The newly introduced lookup dictionary incorporates rich contextual information in training set, which is vital to correctl…
G H Raisoni College of Engg.（G H Raisoni工程学院）；Nagpur University（那格浦尔大学）；SGB Amravati University（SGB阿姆拉瓦蒂大学）
Speech is a natural form of communication for human beings, and computers with the ability to understand speech and speak with a human voice are expected to contribute to the development of more natural man-machine interfaces. Computers with this kind of ability are gradually becoming a reality, through the evolution of speech recognition technologies. Speech is being an important mode of interaction with computers. In this paper Feature extraction is implemented using well-known Mel-Frequency Cepstral Coefficients (MFCC).Pattern matching is done using Dynamic time warping (DTW) algorithm.
This paper introduces SpeeChain, an open-source Pytorch-based toolkit designed to develop the machine speech chain for large-scale use. This first release focuses on the TTS-to-ASR chain, a core component of the machine speech chain, that refers to the TTS data augmentation by unspoken text for ASR. To build an efficient pipeline for the large-scale TTS-to-ASR chain, we implement easy-to-use multi-GPU batch-level model inference, multi-dataloader batch generation, and on-the-fly data selection techniques. In this paper, we first explain the overall procedure of the TTS-to-ASR chain and the dif…
Georgia Institute of Technology（佐治亚理工学院）；Kore University of Enna（恩纳科雷大学）；NTNU（挪威科技大学）
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 th…
Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR) models is a challenge due to the lack of training data. A standard way to address this issue is with shallow fusion methods at inference time. However, due to their dependence on external language models and the deterministic approach to weight boosting, their performance is limited. In this paper, we propose training neural contextual adapters for personalization in neural transducer based ASR models. Our approach can not only bias towards user-defined words, but also has the flexibility to work with pretraine…
We present EasyASR, a distributed machine learning platform for training and serving large-scale Automatic Speech Recognition (ASR) models, as well as collecting and processing audio data at scale. Our platform is built upon the Machine Learning Platform for AI of Alibaba Cloud. Its main functionality is to support efficient learning and inference for end-to-end ASR models on distributed GPU clusters. It allows users to learn ASR models with either pre-defined or user-customized network architectures via simple user interface. On EasyASR, we have produced state-of-the-art results over several …
Unveiling Hidden Factors: Explainable AI for Feature Boosting in Speech Emotion Recognition
University of Québec (TÉLUQ)（魁北克大学（TÉLUQ））；Concordia University（康考迪亚大学）；Concordia Institute for Information Systems Engineering（康考迪亚信息系统工程学院）；University of Québec at Montréal（蒙特利尔魁北克大学）；Centre for Research and Intervention on Suicide, Ethical Issues and End-of-Life Practices（自杀、伦理问题与临终实践研究与干预中心）
Boosting Accuracy and Interpretability in Multilingual Hate Speech Detection Through Layer Freezing and Explainable AI
Department of Computer Science（计算机科学系）；University of South Carolina（南卡罗来纳大学）；Department of Civil, Environmental, and Ocean Engineering（土木、环境与海洋工程系）；Stevens Institute of Technology（史蒂文斯理工学院）；School of Computing（计算学院）；University of Nebraska–Lincoln（内布拉斯加大学林肯分校）；Bowling Green State University（鲍灵格林州立大学）
IBM Research（IBM研究院）；Universidade Federal Fluminense（弗鲁米嫩塞联邦大学）
Most state-of-the-art named entity recognition (NER) systems rely on handcrafted features and on the output of other NLP tasks such as part-of-speech (POS) tagging and text chunking. In this work we propose a language-independent NER system that uses automatically learned features only. Our approach is based on the CharWNN deep neural network, which uses word-level and character-level representations (embeddings) to perform sequential classification. We perform an extensive number of experiments using two annotated corpora in two different languages: HAREM I corpus, which contains texts in Por…
