Where Are We in Semantic Concept Extraction for Spoken Language Understanding?

Ambient clinical documentation technology uses automatic speech recognition (ASR) and natural language processing (NLP) to turn patient-clinician conversations into clinical documentation. It is a promising approach to reducing clinician burden and improving documentation quality. However, the performance of current-generation ASR remains inadequately validated. In this study, we investigated the impact of non-lexical conversational sounds (NLCS) on ASR performance. NLCS, such as Mm-hm and Uh-uh, are commonly used to convey important information in clinical conversations, for example, Mm-hm as a "yes" response from the patient to the clinician question "are you allergic to antibiotics?" In this study, we evaluated 2 contemporary ASR engines, Google Speech-to-Text Clinical Conversation ("Google ASR"), and Amazon Transcribe Medical ("Amazon ASR"), both of which have their language models specifically tailored to clinical conversations. The empirical data used were from 36 primary care encounters. We conducted a series of quantitative and qualitative analyses to examine the word error rate (WER) and the potential impact of misrecognized NLCS on the quality of clinical documentation. Out of a total of 135647 spoken words contained in the evaluation data, 3284 (2.4%) were NLCS. Among these NLCS, 76 (0.06% of total words, 2.3% of all NLCS) were used to convey clinically relevant information. The overall WER, of all spoken words, was 11.8% for Google ASR and 12.8% for Amazon ASR. However, both ASR engines demonstrated poor performance in recognizing NLCS: the WERs across frequently used NLCS were 40.8% (Google) and 57.2% (Amazon), respectively; and among the NLCS that conveyed clinically relevant information, 94.7% and 98.7%, respectively. Current ASR solutions are not capable of properly recognizing NLCS, particularly those that convey clinically relevant information. Although the volume of NLCS in our evaluation data was very small (2.4% of the total corpus; and for NLCS that conveyed clinically relevant information: 0.06%), incorrect recognition of them could result in inaccuracies in clinical documentation and introduce new patient safety risks.

Spoken language understanding (SLU) in dialog systems is generally performed using a natural language understanding (NLU) model based on the hypotheses produced by an automatic speech recognition (ASR) system. However, when new spoken dialog applications are built from scratch in real user environments that often have sub-optimal audio characteristics, ASR performance can suffer due to factors such as the paucity of training data or a mismatch between the training and test data. To address this issue, this paper proposes an ASR-free, end-to-end (E2E) modeling approach to SLU for a cloud-based, modular spoken dialog system (SDS). We evaluate the effectiveness of our approach on crowdsourced data collected from non-native English speakers interacting with a conversational language learning application. Experimental results show that our approach is particularly promising in situations with low ASR accuracy. It can further improve the performance of a sophisticated CNN-based SLU system with more accurate ASR hypotheses by fusing the scores from E2E system, i.e., the overall accuracy of SLU is improved from 85.6% to 86.5%.

End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting

A speech signal captured by a distant microphone is generally smeared by reverberation, which severely degrades automatic speech recognition (ASR) performance. One way to solve this problem is to dereverberate the observed signal prior to ASR. In this paper, a room impulse response is assumed to consist of three parts: a direct-path response, early reflections and late reverberations. Since late reverberations are known to be a major cause of ASR performance degradation, this paper focuses on dealing with the effect of late reverberations. The proposed method first estimates the late reverberations using long-term multi-step linear prediction, and then reduces the late reverberation effect by employing spectral subtraction. The algorithm provided good dereverberation with training data corresponding to the duration of one speech utterance, in our case, less than 6 s. This paper describes the proposed framework for both single-channel and multichannel scenarios. Experimental results showed substantial improvements in ASR performance with real recordings under severe reverberant conditions.

We have used data on patents and publications, and from an Internet-based survey, to analyse corporate technological activities in Automatic Speech Recognition (ASR) and Natural Language Processing (NLP) technologies. Two distinct clusters of firms exist: large firms mainly in telecommunications, desktop computing and consumer electronics; and small firms specialising in speech technologies. The small specialised firms depend heavily on nearby universities and public research institutes and, to some extent, on nearby large firms; their relations with the large firms are complementary as well as competitive. Similar patterns can be observed in other, recently emerging, "new science"-based technologies. Integration between ASR and NLP has so far been weak with the two research communities functioning more or less independently, with the former progressing more rapidly than the latter. Having built technological capabilities in ASR and NLP with a small proportion of their corporate technological resources, the large firms have two options depending on the rate of progress in these technologies (especially NLP) in the future. If it is high, substantial investments (including those in complementary technologies) could open up massive market opportunities. If it is low, modest investments will allow the exploitation of niche markets.

Spoken language understanding (SLU) is a key procedure in task-oriented dialogue systems, its performance has been improved a lot due to deep neural network with pre-trained textual features. However, data sparsity and ASR error usually influence the model performance. Previous studies showed that pre-defined rules and domain knowledge such as lexicon features seems to be helpful for solving these issues. However, those methods are not flexible. In this study, we propose a new domain knowledge, ontology based sememe knowledge, and apply it in SLU task via a weighted sum network. To do so, we construct a sememe knowledge base by identifying slots' meanings and extracting the corresponding sememes from HowNet. We extract sememe sets for characters in given utterance and use them as domain knowledge in SLU task by means of the weighted sum network. Due to the weighted combinations of the sememe sets can extend words' meanings, the proposed method can help the model to flexibly match a sparse word to a specific slot. Evaluation on a Mandarin corpus showed that the proposed approach achieved better performance comparing to a leading method, and it also showed the robustness to ASR error.

End-to-end spoken language understanding (SLU) systems are typically trained on large amounts of data. In many practical scenarios, the amount of labeled speech is often limited as opposed to text. In this study, we investigate the use of non-parallel speech and text to improve the performance of dialog act recognition as an example SLU task. We propose a multiview architecture that can handle each modality separately. To effectively train on such data, this model enforces the internal speech and text encodings to be similar using a shared classifier. On the Switchboard Dialog Act corpus, we show that pretraining the classifier using large amounts of text helps learning better speech encodings, resulting in up to 40% relatively higher classification accuracies. We also show that when the speech embeddings from an automatic speech recognition (ASR) system are used in this framework, the speech-only accuracy exceeds the performance of ASR-text based tests up to 15% relative and approaches the performance of using true transcripts.

Most human interactions occur in the form of spoken conversations where the semantic meaning of a given utterance depends on the context. Each utterance in spoken conversation can be represented by many semantic and speaker attributes, and there has been an interest in building Spoken Language Understanding (SLU) systems for automatically predicting these attributes. Recent work has shown that incorporating dialogue history can help advance SLU performance. However, separate models are used for each SLU task, leading to an increase in inference time and computation cost. Motivated by this, we aim to ask: can we jointly model all the SLU tasks while incorporating context to facilitate low-latency and lightweight inference? To answer this, we propose a novel model architecture that learns dialog context to jointly predict the intent, dialog act, speaker role, and emotion for the spoken utterance. Note that our joint prediction is based on an autoregressive model and we need to decide the prediction order of dialog attributes, which is not trivial. To mitigate the issue, we also propose an order agnostic training method. Our experiments show that our joint model achieves similar results to task-specific classifiers and can effectively integrate dialog context to further improve the SLU performance. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

Spoken language understanding (SLU), which converts user requests in natural language to machine-interpretable expressions, is becoming an essential task. The lack of training data is an important problem, especially for new system tasks, because existing SLU systems are based on statistical approaches. In this paper, we proposed to use two sources of the "wisdom of crowds," crowdsourcing and knowledge community website, for improving the SLU system. We firstly collected paraphrasing variations for new system tasks through crowdsourcing as seed data, and then augmented them using similar questions from a knowledge community website. We investigated the effects of the proposed data augmentation method in SLU task, even with small seed data. In particular, the proposed architecture augmented more than 120,000 samples to improve SLU accuracies.

Machine learning techniques have long been the foundations of speech processing. Bayesian classiflcation, decision trees, unsupervised clustering, the EM algorithm, maximum entropy, etc. are all part of existing speech recognition systems. The success of statistical speech recognition has led to the rise of statistical and empirical methods in natural language processing. Indeed, many of the machine learning techniques used in language processing, from statistical part-of-speech tagging to the noisy channel model for machine translation have roots in work conducted in the speech fleld. However, advances in learning theory and algorithmic machine learning approaches in recent years have led to signiflcant changes in the direction and emphasis of the statistical and learning centered research in natural language processing and made a mark on natural language and speech processing. Approaches such as memory based learning, a range of linear classiflers such as Boosting, SVMs and SNoW and others have been successfully applied to a broad range of natural language problems, and these now inspire new research in speech retrieval and recognition. We have seen an increasingly close collaboration between voice and language processing researchers in some of the shared tasks such as spontaneous speech recognition and understanding, voice data information extraction, and machine translation. The purpose of this special issue was to invite speech and language researchers to communicate with each other, and with the machine learning community on the latest machine learning advances in their work. The call for papers was met with great enthusiasm from the speech and natural language community. Thirty six submissions were received; each paper was reviewed by at least three reviewers. Only ten papers were selected re∞ecting not only some of the best work on machine learning in the areas of natural language and spoken language processing but also what we view as a collection of papers that represent current trends in these areas of research both from the perspective of

In this paper, we present an approach to Spoken Language Understanding (SLU) where we perform a combination of multiple hypotheses from several Automatic Speech Recognizers (ASRs) in order to reduce the impact of recognition errors in the SLU module. This combination is performed using a Grammatical Inference algorithm that provides a generalization of the input sentences by means of a weighted graph of words. We have also developed a specific SLU algorithm that is able to process these graphs of words according to a stochastic semantic modelling.The results show that the combinations of several hypotheses from the ASR module outperform the results obtained by taking just the 1-best transcription.

Named Entity Recognition is a subtask in Information Extraction. In Named Entity Recognition (NER) we try to identify each of the words provided into some categories predefined by us. These categories or classes can be organization, name, time, place etc. Named Entity Recognition is a part of Natural Language Processing which is aims at making human and computer interactions more meaningful and efficient. NLP is nowadays being effectively being used in the area of automatic text summarization, cross language information retrieval, speech recognition and query named entity recognition. This paper focuses on Named entity recognition, how it is performed and a how apply NER to web search queries so that correct and more user personalized results are displayed by the web search engines..

Spoken Language Understanding (SLU) is a part of spoken dialogue system (SDS) which represents speech data into semantic form required to understand user's intention. The human-computer interaction system is most commonly placed in noisy environment. This introduces error in Automatic Speech Recognizer (ASR). SLU takes into account ASR errors. Thus robustness of SLU plays important role in efficient working of human computer interaction system. The SLU consist of semantic decoder and belief tracker. Recent line of research models semantic decoder as a classification task or sequence to sequence learning. The SLU models incorporate learning models for classification. The learning model requires lot of labelled data for training. The process of obtaining labelled data is expensive and time consuming. Thus it is desirable that SLU must be able to maintain its accuracy even if sparse training data is available. The objective of this research is to evaluate robustness in terms of accuracy and data sparsity of SLU incorporating Relevance Vector Classifier (RVC) and Stochastic Gradient Descent (SGD) classifier. The framework of SLU incorporates semantic tuple classifier (STC). The STC performs dialogue act classification and slot filling by using classifiers. The classifiers that were incorporated in semantic decoder are Support Vector Machine (SVM), SGD and RVC. The dataset used is DSTC II. The SVM classifier showed maximum robustness and better accuracy as compared to other classifiers. For SVM, classifier the Inter Cross Entropy (ICE) and accuracy were 1.0 and 0.91, respectively. For RVC, ICE and accuracy were 4.055 and 0.52.

Combined speech enhancement and auditory modelling for robust distributed speech recognition

Human-computer interaction (HCI) is significantly impacted by delayed responses from a spoken dialogue system. Hence, end-to-end (e2e) spoken language understanding (SLU) solutions have recently been proposed to decrease latency. Such approaches allow for the extraction of semantic information directly from the speech signal, thus bypassing the need for a transcript from an automatic speech recognition (ASR) system. In this paper, we propose a compact e2e SLU architecture for streaming scenarios, where chunks of the speech signal are processed continuously to predict intent and slot values. Our model is based on a 3D convolutional neural network (3D-CNN) and a unidirectional long short-term memory (LSTM). We compare the performance of two alignment-free losses: the connectionist temporal classification (CTC) method and its adapted version, namely connectionist temporal localization (CTL). The latter performs not only the classification but also localization of sequential audio events. The proposed solution is evaluated on the Fluent Speech Command dataset and results show our model ability to process incoming speech signal, reaching accuracy as high as 98.97 % for CTC and 98.78 % for CTL on single-label classification, and as high as 95.69 % for CTC and 95.28 % for CTL on two-label prediction.