A new label smoothing method that makes use of prior knowledge of a language at human level, homophone, is proposed in this paper for automatic speech recognition (ASR). Compared with its forerunners, the proposed method uses pronunciation knowledge of homophones in a more complex way. End-to-end ASR models that learn acoustic model and language model jointly and modelling units of characters are necessary conditions for this method. Experiments with hybrid CTC sequence-to-sequence model show that the new method can reduce character error rate (CER) by 0.4% absolutely.
Homophone characters are common in tonal syllable-based languages, such as Mandarin and Cantonese. The data-intensive end-to-end Automatic Speech Recognition (ASR) systems are more likely to mis-recognize homophone characters and rare words under low-resource settings. For the problem of lowresource Cantonese speech recognition, this paper presents a novel homophone extension method to integrate human knowledge of the homophone lexicon into the beam search decoding process with language model re-scoring. Besides, we propose an automatic unified writing method to merge the variants of Cantonese…
Generating spoken word embeddings that possess semantic information is a fascinating topic. Compared with text-based embeddings, they cover both phonetic and semantic characteristics, which can provide richer information and are potentially helpful for improving ASR and speech translation systems. In this paper, we review and examine the authenticity of a seminal work in this field: Speech2Vec. First, a homophone-based inspection method is proposed to check the speech embeddings released by the author of Speech2Vec. There is no indication that these embeddings are generated by the Speech2Vec m…
National Institute of Information and Communications Technology (NICT)（日本国立信息与通信技术研究所）
For Mandarin end-to-end (E2E) automatic speech recognition (ASR) tasks, compared to character-based modeling units, pronunciation-based modeling units could improve the sharing of modeling units in model training but meet homophone problems. In this study, we propose to use a novel pronunciation-aware unique character encoding for building E2E RNN-T-based Mandarin ASR systems. The proposed encoding is a combination of pronunciation-base syllable and character index (CI). By introducing the CI, the RNN-T model can overcome the homophone problem while utilizing the pronunciation information for …
Automatic speech recognition (ASR) meets more informal and free-form input data as voice user interfaces and conversational agents such as the voice assistants such as Alexa, Google Home, etc., gain popularity. Conversational speech is both the most difficult and environmentally relevant sort of data for speech recognition. In this paper, we take a linguistic perspective, and take the French language as a case study toward disambiguation of the French homophones. Our contribution aims to provide more insight into human speech transcription accuracy in conditions to reproduce those of state-of-…
Nowadays voice search for points of interest (POI) is becoming increasingly popular. However, speech recognition for local POI has remained to be a challenge due to multi-dialect and massive POI. This paper improves speech recognition accuracy for local POI from two aspects. Firstly, a geographic acoustic model (Geo-AM) is proposed. The Geo-AM deals with multi-dialect problem using dialect-specific input feature and dialect-specific top layer. Secondly, a group of geo-specific language models (Geo-LMs) are integrated into our speech recognition system to improve recognition accuracy of long ta…
Mandarin Humorous Homophone Recognition and Disambiguation in Automatic Speech Recognition
blind Anonymous to ISCSLP 1 School of Computer Science \& Engineering, UNSW Sydney, Australia 2 School of Electrical Engineering \& Telecommunications, UNSW Sydney, Australia
Connectionist Temporal Classification (CTC) based end-to-end speech recognition system usually need to incorporate an external language model by using WFST-based decoding in order to achieve promising results. This is more essential to Mandarin speech recognition since it owns a special phenomenon, namely homophone, which causes a lot of substitution errors. The linguistic information introduced by language model will help to distinguish these substitution errors. In this work, we propose a transformer based spelling correction model to automatically correct errors especially the substitution …
IBM Research AI（IBM研究院人工智能部）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；IBM Research Tokyo（IBM东京研究院）
We introduce two techniques, length perturbation and n-best based label smoothing, to improve generalization of deep neural network (DNN) acoustic models for automatic speech recognition (ASR). Length perturbation is a data augmentation algorithm that randomly drops and inserts frames of an utterance to alter the length of the speech feature sequence. N-best based label smoothing randomly injects noise to ground truth labels during training in order to avoid overfitting, where the noisy labels are generated from n-best hypotheses. We evaluate these two techniques extensively on the 300-hour Sw…
While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks, the Randomized Smoothing paradigm has been shown to be effective at defending models. However, it is difficult to apply this paradigm to ASR tasks, due to their complexity and the sequential nature of their outputs. Our paper overcomes some of these challenges by leveraging speech-specific tools like enhancement and ROVER voting to design an ASR model that i…
Echotune: A Modular Extractor Leveraging the Variable-Length Nature of Speech in ASR Tasks
Blockchain Industry School, Chengdu University of Information Technology（成都信息工程大学区块链产业学院）；School of Computer Science and Technology, Fudan University（复旦大学计算机科学技术学院）；Department of Computer Science, Victoria University（维多利亚大学计算机科学系）
Stellenbosch University（斯泰伦博斯大学）；National University of Singapore（新加坡国立大学）
This paper considers the impact of automatic segmentation on the fully-automatic, semi-supervised training of automatic speech recognition (ASR) systems for five-lingual code-switched (CS) speech. Four automatic segmentation techniques were evaluated in terms of the recognition performance of an ASR system trained on the resulting segments in a semi-supervised manner. The system's output was compared with the recognition rates achieved by a semi-supervised system trained on manually assigned segments. Three of the automatic techniques use a newly proposed convolutional neural network (CNN) mod…
Recently, end-to-end speech recognition with a hybrid model consisting of the connectionist temporal classification(CTC) and the attention encoder-decoder achieved state-of-the-art results. In this paper, we propose a novel CTC decoder structure based on the experiments we conducted and explore the relation between decoding performance and the depth of encoder. We also apply attention smoothing mechanism to acquire more context information for subword-based decoding. Taken together, these strategies allow us to achieve a word error rate(WER) of 4.43% without LM and 3.34% with RNN-LM on the tes…
Recently, there has been a growing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. In this paper, we explore the use of attention-based encoder-decoder model for Mandarin speech recognition on a voice search task. Previous attempts have shown that applying attention-based encoder-decoder to Mandarin speech recognition was quite difficult due to the logographic orthography of Mandarin, the large vocabulary and the conditional dependency of the attention model. In this paper, we use character embedding to deal with the large v…
Following the rationale of end-to-end modeling, CTC, RNN-T or encoder-decoder-attention models for automatic speech recognition (ASR) use graphemes or grapheme-based subword units based on e.g. byte-pair encoding (BPE). The mapping from pronunciation to spelling is learned completely from data. In contrast to this, classical approaches to ASR employ secondary knowledge sources in the form of phoneme lists to define phonetic output labels and pronunciation lexica. In this work, we do a systematic comparison between grapheme- and phoneme-based output labels for an encoder-decoder-attention ASR m…
Conversational speech recognition has served as a flagship speech recognition task since the release of the Switchboard corpus in the 1990s. In this paper, we measure the human error rate on the widely used NIST 2000 test set, and find that our latest automated system has reached human parity. The error rate of professional transcribers is 5.9% for the Switchboard portion of the data, in which newly acquainted pairs of people discuss an assigned topic, and 11.3% for the CallHome portion where friends and family members have open-ended conversations. In both cases, our automated system establis…
Sony Corporation（索尼公司）；Carnegie Mellon University（卡内基梅隆大学）
Although end-to-end automatic speech recognition (E2E ASR) has achieved great performance in tasks that have numerous paired data, it is still challenging to make E2E ASR robust against noisy and low-resource conditions. In this study, we investigated data augmentation methods for E2E ASR in distant-talk scenarios. E2E ASR models are trained on the series of CHiME challenge datasets, which are suitable tasks for studying robustness against noisy and spontaneous speech. We propose to use three augmentation methods and thier combinations: 1) data augmentation using text-to-speech (TTS) data, 2) …
Sony Group Corporation（索尼集团公司）；Carnegie Mellon University（卡内基梅隆大学）
End-to-end automatic speech recognition suffers from adaptation to unknown target domain speech despite being trained with a large amount of paired audio--text data. Recent studies estimate a linguistic bias of the model as the internal language model (LM). To effectively adapt to the target domain, the internal LM is subtracted from the posterior during inference and fused with an external target-domain LM. However, this fusion complicates the inference and the estimation of the internal LM may not always be accurate. In this paper, we propose a simple external LM fusion method for domain ada…
Duke Kunshan University（昆山杜克大学）；Wuhan University（武汉大学）
Textual escalation detection has been widely applied to e-commerce companies' customer service systems to pre-alert and prevent potential conflicts. Similarly, in public areas such as airports and train stations, where many impersonal conversations frequently take place, acoustic-based escalation detection systems are also useful to enhance passengers' safety and maintain public order. To this end, we introduce a system based on acoustic-lexical features to detect escalation from speech, Voice Activity Detection (VAD) and label smoothing are adopted to further enhance the performance in our ex…
Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural network. In previous work, we have shown that such architectures are comparable to state-of-theart ASR systems on dictation tasks, but it was not clear if such architectures would be practical for more challenging tasks such as voice search. In this work, we explore a variety of structural and optimization improvements to our LAS model which significantly improve p…
Mandarin-English code-switching (CS) is frequently used among East and Southeast Asian people. However, the intra-sentence language switching of the two very different languages makes recognizing CS speech challenging. Meanwhile, the recent successful non-autoregressive (NAR) ASR models remove the need for left-to-right beam decoding in autoregressive (AR) models and achieved outstanding performance and fast inference speed, but it has not been applied to Mandarin-English CS speech recognition. This paper takes advantage of the Mask-CTC NAR ASR framework to tackle the CS speech recognition iss…
Achieving high accuracy with end-to-end speech recognizers requires careful parameter initialization prior to training. Otherwise, the networks may fail to find a good local optimum. This is particularly true for online networks, such as unidirectional LSTMs. Currently, the best strategy to train such systems is to bootstrap the training from a tied-triphone system. However, this is time consuming, and more importantly, is impossible for languages without a high-quality pronunciation lexicon. In this work, we propose an initialization strategy that uses teacher-student learning to transfer kno…
In Indian Languages , native speakers are able to understand new words formed by either combining or modifying root words with tense and / or gender. Due to data insufficiency, Automatic Speech Recognition system (ASR) may not accommodate all the words in the language model irrespective of the size of the text corpus. It also becomes computationally challenging if the volume of the data increases exponentially due to morphological changes to the root word. In this paper a new unsupervised method is proposed for a Indian language: Telugu, based on the unsupervised method for Hindi, to generate …
Punctuation prediction for automatic speech recognition (ASR) output transcripts plays a crucial role for improving the readability of the ASR transcripts and for improving the performance of downstream natural language processing applications. However, achieving good performance on punctuation prediction often requires large amounts of labeled speech transcripts, which is expensive and laborious. In this paper, we propose a Discriminative Self-Training approach with weighted loss and discriminative label smoothing to exploit unlabeled speech transcripts. Experimental results on the English IW…
Shandong University（山东大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Boston University（波士顿大学）；Indiana University Bloomington（印第安纳大学伯明顿分校）
With the wide use of Automatic Speech Recognition (ASR) in applications such as human machine interaction, simultaneous interpretation, audio transcription, etc., its security protection becomes increasingly important. Although recent studies have brought to light the weaknesses of popular ASR systems that enable out-of-band signal attack, adversarial attack, etc., and further proposed various remedies (signal smoothing, adversarial training, etc.), a systematic understanding of ASR security (both attacks and defenses) is still missing, especially on how realistic such threats are and how gene…
NTT Media Intelligence Laboratories（NTT媒体情报实验室）；NTT Corporation（NTT公司）
This paper is the first study to apply deep mutual learning (DML) to end-to-end ASR models. In DML, multiple models are trained simultaneously and collaboratively by mimicking each other throughout the training process, which helps to attain the global optimum and prevent models from making over-confident predictions. While previous studies applied DML to simple multi-class classification problems, there are no studies that have used it on more complex sequence-to-sequence mapping problems. For this reason, this paper presents a method to apply DML to state-of-the-art Transformer-based end-to-…
We examine the effect of data augmentation for training of language models for speech recognition. We compare augmentation based on global error statistics with one based on per-word unigram statistics of ASR errors and observe that it is better to only pay attention the global substitution, deletion and insertion rates. This simple scheme also performs consistently better than label smoothing and its sampled variants. Additionally, we investigate into the behavior of perplexity estimated on augmented data, but conclude that it gives no better prediction of the final error rate. Our best augme…
University of Helsinki（赫尔辛基大学）；Omilia - Conversational Intelligence（Omilia对话智能公司）；Brno University of Technology（布尔诺理工大学）
When recognizing emotions from speech, we encounter two common problems: how to optimally capture emotion-relevant information from the speech signal and how to best quantify or categorize the noisy subjective emotion labels. Self-supervised pre-trained representations can robustly capture information from speech enabling state-of-the-art results in many downstream tasks including emotion recognition. However, better ways of aggregating the information across time need to be considered as the relevant emotion information is likely to appear piecewise and not uniformly across the signal. For th…
Phoneme-based acoustic modeling of large vocabulary automatic speech recognition takes advantage of phoneme context. The large number of context-dependent (CD) phonemes and their highly varying statistics require tying or smoothing to enable robust training. Usually, classification and regression trees are used for phonetic clustering, which is standard in hidden Markov model (HMM)-based systems. However, this solution introduces a secondary training objective and does not allow for end-to-end training. In this work, we address a direct phonetic context modeling for the hybrid deep neural netw…
STC-Innovations Ltd（STC创新有限公司）；LIUM, University of Le Mans（勒芒大学LIUM实验室）；ITMO University（圣彼得堡国立信息技术机械与光学大学）
This work proposes a novel approach to out-of-vocabulary (OOV) keyword search (KWS) task. The proposed approach is based on using high-level features from an automatic speech recognition (ASR) system, so called phoneme posterior based (PPB) features, for decoding. These features are obtained by calculating time-dependent phoneme posterior probabilities from word lattices, followed by their smoothing. For the PPB features we developed a special novel very fast, simple and efficient OOV decoder. Experimental results are presented on the Georgian language from the IARPA Babel Program, which was t…
In speech emotion recognition tasks, models learn emotional representations from datasets. We find the data distribution in the IEMOCAP dataset is very imbalanced, which may harm models to learn a better representation. To address this issue, we propose a novel Pairwise-emotion Data Distribution Smoothing (PDDS) method. PDDS considers that the distribution of emotional data should be smooth in reality, then applies Gaussian smoothing to emotion-pairs for constructing a new training set with a smoother distribution. The required new data are complemented using the mixup augmentation. As PDDS is…
USC Ming Hsieh Department of Electrical and Computer Engineering（南加州大学明谢电子与计算机工程系）
A variety of recent works have looked into defenses for deep neural networks against adversarial attacks particularly within the image processing domain. Speech processing applications such as automatic speech recognition (ASR) are increasingly relying on deep learning models, and so are also prone to adversarial attacks. However, many of the defenses explored for ASR simply adapt the image-domain defenses, which may not provide optimal robustness. This paper explores speech specific defenses using the mel spectral domain, and introduces a novel defense method called 'mel domain noise flooding…
Discriminative training techniques define state-of-the-art performance for automatic speech recognition systems. However, they are inherently prone to overfitting, leading to poor generalization performance when using limited training data. In order to address this issue, this paper presents a full Bayesian framework to account for model uncertainty in sequence discriminative training of factored TDNN acoustic models. Several Bayesian learning based TDNN variant systems are proposed to model the uncertainty over weight parameters and choices of hidden activation functions, or the hidden layer …
