Spoken Language Understanding System Research Articles

Benefits of pre-trained mono- and cross-lingual speech representations for spoken language understanding of Dutch dysarthric speech

With the rise of deep learning, spoken language understanding (SLU) for command-and-control applications such as a voice-controlled virtual assistant can offer reliable hands-free operation to physically disabled individuals. However, due to data scarcity, it is still a challenge to process dysarthric speech. Pre-training (part of) the SLU model with supervised automatic speech recognition (ASR) targets or with self-supervised learning (SSL) may help to overcome a lack of data, but no research has shown which pre-training strategy performs better for SLU on dysarthric speech and to which extent the SLU task benefits from knowledge transfer from pre-training with dysarthric acoustic tasks. This work aims to compare different mono- or cross-lingual pre-training (supervised and unsupervised) methodologies and quantitatively investigates the benefits of pre-training for SLU tasks on Dutch dysarthric speech. The designed SLU systems consist of a pre-trained speech representations encoder and a SLU decoder to map encoded features to intents. Four types of pre-trained encoders, a mono-lingual time-delay neural network (TDNN) acoustic model, a mono-lingual transformer acoustic model, a cross-lingual transformer acoustic model (Whisper), and a cross-lingual SSL Wav2Vec2.0 model (XLSR-53), are evaluated complemented with three types of SLU decoders: non-negative matrix factorization (NMF), capsule networks, and long short-term memory (LSTM) networks. The acoustic analysis of the four pre-trained encoders are tested on Dutch dysarthric home-automation data with word error rate (WER) results to investigate the correlations of the dysarthric acoustic task (ASR) and the semantic task (SLU). By introducing the intelligibility score (IS) as a metric of the impairment severity, this paper further quantitatively analyzes dysarthria-severity-dependent models for SLU tasks.

Knowing Where to Leverage: Context-Aware Graph Convolutional Network With an Adaptive Fusion Layer for Contextual Spoken Language Understanding

Spoken language understanding (SLU) systems aim to understand users’ utterance, which is a key component of task-oriented dialogue systems. In this paper, we focus on improving the contextual SLU. The contextual SLU systems mainly focus on how to effectively incorporate dialog context information (contextual information). The existing approaches all use the same contextual information to guide slot filling at all tokens, which may inject the irrelevant information and result in ambiguity. To tackle this problem, we propose a context-aware graph convolutional network (GCN) with an adaptive fusion layer for contextual SLU. The context-aware GCN is proposed to automatically aggregate the contextual information, which frees our model from the manually designed heuristic aggregation function. Meanwhile, an adaptive fusion layer is applied at each token to dynamically incorporate relevant contextual information, which achieves a fine-grained contextual information transfer to guide the token-level slot filling. Experiments on the Simulated Dialog Dataset show that our model achieves state-of-the-art performance and outperforms other previous methods by a large margin (+3.67% on Sim-R, +4.18% on Sim-M and +3.75% on Overall dataset). In addition, we explore and analyze the pre-trained model (i.e., BERT) in our framework. We show that incorporating BERT brings a large improvement in low-resource setting.

Low resource end-to-end spoken language understanding with capsule networks

Designing a Spoken Language Understanding (SLU) system for command-and-control applications is challenging. Both Automatic Speech Recognition and Natural Language Understanding are language and application dependent to a great extent. Even with a lot of design effort, users often still have to know what to say to the system for it to do what they want. We propose to use an end-to-end SLU system that maps speech directly to semantics and that can be trained by the user through demonstrations. The user can teach the system a new command by uttering the command and subsequently demonstrating its meaning through an alternative interface. The system will learn the mapping from the spoken command to the task. The dependency on the user also allows different languages and non-standard or impaired speech as valid inputs. Teaching the system requires effort from the user, so it is crucial that the system learns quickly. In this paper we propose to use capsule networks for this task, which are believed to be data efficient. We discuss two architectures for using capsule networks. We analyse their performance and compare them with two baseline systems, one based on Non-negative Matrix Factorisation (NMF) which has been successful for this task and one encoder-decoder approach. We show that in most cases the capsule network performs better than the baseline systems. Furthermore, we demonstrate the versatility of the architecture by inferring speaker identity and the user’s word choice through multitask learning.

Graph LSTM with Context-Gated Mechanism for Spoken Language Understanding

Much research in recent years has focused on spoken language understanding (SLU), which usually involves two tasks: intent detection and slot filling. Since Yao et al.(2013), almost all SLU systems are RNN-based, which have been shown to suffer various limitations due to their sequential nature. In this paper, we propose to tackle this task with Graph LSTM, which first converts text into a graph and then utilizes the message passing mechanism to learn the node representation. Not only the Graph LSTM addresses the limitations of sequential models, but it can also help to utilize the semantic correlation between slot and intent. We further propose a context-gated mechanism to make better use of context information for slot filling. Our extensive evaluation shows that the proposed model outperforms the state-of-the-art results by a large margin.

Joint Discriminative Decoding of Words and Semantic Tags for Spoken Language Understanding

Most Spoken Language Understanding (SLU) systems today employ a cascade approach, where the best hypothesis from Automatic Speech Recognizer (ASR) is fed into understanding modules such as slot sequence classifiers and intent detectors. The output of these modules is then further fed into downstream components such as interpreter and/or knowledge broker. These statistical models are usually trained individually to optimize the error rate of their respective output. In such approaches, errors from one module irreversibly propagates into other modules causing a serious degradation in the overall performance of the SLU system. Thus it is desirable to jointly optimize all the statistical models together. As a first step towards this, in this paper, we propose a joint decoding framework in which we predict the optimal word as well as slot sequence (semantic tag sequence) jointly given the input acoustic stream. Furthermore, the improved recognition output is then used for an utterance classification task, specifically, we focus on intent detection task. On a SLU task, we show 1.5% absolute reduction (7.6% relative reduction) in word error rate (WER) and 1.2% absolute improvement in F measure for slot prediction when compared to a very strong cascade baseline comprising of state-of-the-art large vocabulary ASR followed by conditional random field (CRF) based slot sequence tagger. Similarly, for intent detection, we show 1.2% absolute reduction (12% relative reduction) in classification error rate.

Spoken language understanding

Semantics deals with the organization of meanings and the relations between sensory signs or symbols and what they denote or mean. Computational semantics performs a conceptualization of the world using computational processes for composing a meaning representation structure from available signs and their features present, for example, in words and sentences. Spoken language understanding (SLU) is the interpretation of signs conveyed by a speech signal. SLU and natural language understanding (NLU) share the goal of obtaining a conceptual representation of natural language sentences. Specific to SLU is the fact that signs to be used for interpretation are coded into signals along with other information such as speaker identity. Furthermore, spoken sentences often do not follow the grammar of a language; they exhibit self-corrections, hesitations, repetitions, and other irregular phenomena. SLU systems contain an automatic speech recognition (ASR) component and must be robust to noise due to the spontaneous nature of spoken language and the errors introduced by ASR. Moreover, ASR components output a stream of words with no structure information like punctuation and sentence boundaries. Therefore, SLU systems cannot rely on such markers and must perform text segmentation and understanding at the same time.

The AT&T spoken language understanding system

Spoken language understanding (SLU) aims at extracting meaning from natural language speech. Over the past decade, a variety of practical goal-oriented spoken dialog systems have been built for limited domains. SLU in these systems ranges from understanding predetermined phrases through fixed grammars, extracting some predefined named entities, extracting users' intents for call classification, to combinations of users' intents and named entities. In this paper, we present the SLU system of VoiceTone/spl reg/ (a service provided by ATT 2) extending statistical classifiers to seamlessly integrate hand crafted classification rules with the rules learned from data; and 3) developing an active learning framework to minimize the human labeling effort for quickly building the classifier models and adapting them to changes. We present an evaluation of this system using two deployed applications of VoiceTone/spl reg/.

Spoken language understanding using the Hidden Vector State Model

The Hidden Vector State (HVS) Model is an extension of the basic discrete Markov model in which context is encoded as a stack-oriented state vector. State transitions are factored into a stack shift operation similar to those of a push-down automaton followed by the push of a new preterminal category label. When used as a semantic parser, the model can capture hierarchical structure without the use of treebank data for training and it can be trained automatically using expectation-maximization (EM) from only-lightly annotated training data. When deployed in a system, the model can be continually refined as more data becomes available. In this paper, the practical application of the model in a spoken language understanding system (SLU) is described. Through a sequence of experiments, the issues of robustness to noise and portability to similar and extended domains are investigated. The end-to-end performance obtained from experiments in the ATIS domain show that the system is comparable to existing SLU systems which rely on either hand-crafted semantic grammar rules or statistical models trained on fully annotated training corpora. Experiments using data which have been artificially corrupted with varying levels of additive noise show that the HVS-based parser is relatively robust, and experiments using data sets from other domains indicate that the overall framework allows adaptation to related domains, and scaling to cover enlarged domains. In summary, it is argued that constrained statistical parsers such as the HVS model allow robust spoken dialogue systems to be built at relatively low cost, and which can be automatically adapted as new data is acquired both to improve performance and extend coverage.