Spoken language understanding (SLU) tasks are usually solved by first transcribing an utterance with automatic speech recognition (ASR) and then feeding the output to a text-based model. Recent advances in self-supervised representation learning for speech data have focused on improving the ASR component. We investigate whether representation learning for speech has matured enough to replace ASR in SLU. We compare learned speech features from wav2vec 2.0, state-of-the-art ASR transcripts, and the ground truth text as input for a novel speech-based named entity recognition task, a cardiac arrest detection task on real-world emergency calls and two existing SLU benchmarks. We show that learned speech features are superior to ASR transcripts on three classification tasks. For machine translation, ASR transcripts are still the better choice. We highlight the intrinsic robustness of wav2vec 2.0 representations to out-of-vocabulary words as key to better performance.
As Automatic Speech Processing (ASR) systems are getting better, there is an increasing interest of using the ASR output to do downstream Natural Language Processing (NLP) tasks. However, there are few open source toolkits that can be used to generate reproducible results on different Spoken Language Understanding (SLU) benchmarks. Hence, there is a need to build an open source standard that can be used to have a faster start into SLU research. We present ESPnet-SLU, which is designed for quick development of spoken language understanding in a single framework. ESPnet-SLU is a project inside end-to-end speech processing toolkit, ESPnet, which is a widely used open-source standard for various speech processing tasks like ASR, Text to Speech (TTS) and Speech Translation (ST). We enhance the toolkit to provide implementations for various SLU benchmarks that enable researchers to seamlessly mix-and-match different ASR and NLU models. We also provide pretrained models with intensively tuned hyper-parameters that can match or even outperform the current state-of-the-art performances. The toolkit is publicly available at https://github.com/espnet/espnet.
Lattices form a compact representation of multiple hypotheses generated from an automatic speech recognition system and have been shown to improve performance of downstream tasks like spoken language understanding and speech translation, compared to using one-best hypothesis. In this work, we look into the effectiveness of lattice cues for rescoring n-best lists in second-pass. We encode lattices with a recurrent network and train an attention encoder-decoder model for n-best rescoring. The rescoring model with attention to lattices achieves 4-5% relative word error rate reduction over first-pass and 6-8% with attention to both lattices and acoustic features. We show that rescoring models with attention to lattices outperform models with attention to n-best hypotheses. We also study different ways to incorporate lattice weights in the lattice encoder and demonstrate their importance for n-best rescoring.
Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in higher-level spoken language understanding tasks, including using end-to-end models, but there are fewer annotated datasets for such tasks. At the same time, recent work shows the possibility of pre-training generic representations and then fine-tuning for several tasks using relatively little labeled data. We propose to create a suite of benchmark tasks for Spoken Language Understanding Evaluation (SLUE) consisting of limited-size labeled training sets and corresponding evaluation sets. This resource would allow the research community to track progress, evaluate pre-trained representations for higher-level tasks, and study open questions such as the utility of pipeline versus end-to-end approaches. We present the first phase of the SLUE benchmark suite, consisting of named entity recognition, sentiment analysis, and ASR on the corresponding datasets. We focus on naturally produced (not read or synthesized) speech, and freely available datasets. We provide new transcriptions and annotations on subsets of the VoxCeleb and VoxPopuli datasets, evaluation metrics and results for baseline models, and an open-source toolkit to reproduce the baselines and evaluate new models.
Speech self-supervised models such as wav2vec 2.0 and HuBERT are making revolutionary progress in Automatic Speech Recognition (ASR). However, they have not been totally proven to produce better performance on tasks other than ASR. In this work, we explored partial fine-tuning and entire fine-tuning on wav2vec 2.0 and HuBERT pre-trained models for three non-ASR speech tasks: Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding. With simple proposed downstream frameworks, the best scores reached 79.58% weighted accuracy on speaker-dependent setting and 73.01% weighted accuracy on speaker-independent setting for Speech Emotion Recognition on IEMOCAP, 2.36% equal error rate for Speaker Verification on VoxCeleb1, 89.38% accuracy for Intent Classification and 78.92% F1 for Slot Filling on SLURP, showing the strength of fine-tuned wav2vec 2.0 and HuBERT on learning prosodic, voice-print and semantic representations.
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 consists of a shared audio encoder and three decoders, two of which are seq-to-seq decoders that predict non null slot tags and slot values in parallel and in an auto-regressive manner. FANS neural encoder and decoders architectures are flexible which allows us to leverage different combinations of LSTM, self-attention, and attenders. Our experiments show compared to the state-of-the-art end-to-end SLU models, FANS reduces ICER and IRER errors relatively by 30 % and 7 %, respectively, when tested on an in-house SLU dataset and by 0.86 % and 2 % absolute when tested on a public SLU dataset.
Building Spoken Language Understanding (SLU) systems that do not rely on language specific Automatic Speech Recognition (ASR) is an important yet less explored problem in language processing. In this paper, we present a comparative study aimed at employing a pre-trained acoustic model to perform SLU in low resource scenarios. Specifically, we use three different embeddings extracted using Allosaurus, a pre-trained universal phone decoder: (1) Phone (2) Panphone, and (3) Allo embeddings. These embeddings are then used in identifying the spoken intent. We perform experiments across three different languages: English, Sinhala, and Tamil each with different data sizes to simulate high, medium, and low resource scenarios. Our system improves on the state-of-the-art (SOTA) intent classification accuracy by approximately 2.11% for Sinhala and 7.00% for Tamil and achieves competitive results on English. Furthermore, we present a quantitative analysis of how the performance scales with the number of training examples used per intent.
Speech summarization is typically performed by using a cascade of speech recognition and text summarization models. End-to-end modeling of speech summarization models is challenging due to memory and compute constraints arising from long input audio sequences. Recent work in document summarization has inspired methods to reduce the complexity of self-attentions, which enables transformer models to handle long sequences. In this work, we introduce a single model optimized end-to-end for speech summarization. We apply the restricted self-attention technique from text-based models to speech models to address the memory and compute constraints. We demonstrate that the proposed model learns to directly summarize speech for the How-2 corpus of instructional videos. The proposed end-to-end model outperforms the previously proposed cascaded model by 3 points absolute on ROUGE. Further, we consider the spoken language understanding task of predicting concepts from speech inputs and show that the proposed end-to-end model outperforms the cascade model by 4 points absolute F-1.
A large-scale conversational agent can suffer from understanding user utterances with various ambiguities such as ASR ambiguity, intent ambiguity, and hypothesis ambiguity. When ambiguities are detected, the agent should engage in a clarifying dialog to resolve the ambiguities before committing to actions. However, asking clarifying questions for all the ambiguity occurrences could lead to asking too many questions, essentially hampering the user experience. To trigger clarifying questions only when necessary for the user satisfaction, we propose a neural self-attentive model that leverages the hypotheses with ambiguities and contextual signals. We conduct extensive experiments on five common ambiguity types using real data from a large-scale commercial conversational agent and demonstrate significant improvement over a set of baseline approaches.
Intent detection (ID) and Slot filling (SF) are two major tasks in spoken language understanding (SLU). Recently, attention mechanism has been shown to be effective in jointly optimizing these two tasks in an interactive manner. However, latest attention-based works concentrated only on the first-order attention design, while ignoring the exploration of higher-order attention mechanisms. In this paper, we propose a BiLinear attention block, which leverages bilinear pooling to simultaneously exploit both the contextual and channel-wise bilinear attention distributions to capture the second-order interactions between the input intent or slot features. Higher and even infinity order interactions are built by stacking numerous blocks and assigning Exponential Linear Unit (ELU) to blocks. Before the decoding stage, we introduce the Dynamic Feature Fusion Layer to implicitly fuse intent and slot information in a more effective way. Technically, instead of simply concatenating intent and slot features, we first compute two correlation matrices to weight on two features. Furthermore, we present Higher-order Attention Network for the SLU tasks. Experiments on two benchmark datasets show that our approach yields improvements compared with the state-of-the-art approach. We also provide discussion to demonstrate the effectiveness of the proposed approach.
Language Models (LMs) have been ubiquitously leveraged in various tasks including spoken language understanding (SLU). Spoken language requires careful understanding of speaker interactions, dialog states and speech induced multimodal behaviors to generate a meaningful representation of the conversation. In this work, we propose to dissect SLU into three representative properties:conversational (disfluency, pause, overtalk), channel (speaker-type, turn-tasks) and ASR (insertion, deletion,substitution). We probe BERT based language models (BERT, RoBERTa) trained on spoken transcripts to investigate its ability to understand multifarious properties in absence of any speech cues. Empirical results indicate that LM is surprisingly good at capturing conversational properties such as pause prediction and overtalk detection from lexical tokens. On the downsides, the LM scores low on turn-tasks and ASR errors predictions. Additionally, pre-training the LM on spoken transcripts restrain its linguistic understanding. Finally, we establish the efficacy and transferability of the mentioned properties on two benchmark datasets: Switchboard Dialog Act and Disfluency datasets.
Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource target languages, the augmented data sets are often noisy, and thus impede the performance of SLU models. In this paper we focus on mitigating noise in augmented data. We develop a denoising training approach. Multiple models are trained with data produced by various augmented methods. Those models provide supervision signals to each other. The experimental results show that our method outperforms the existing state of the art by 3.05 and 4.24 percentage points on two benchmark datasets, respectively. The code will be made open sourced on github.
The success of interactive dialog systems is usually associated with the quality of the spoken language understanding (SLU) task, which mainly identifies the corresponding dialog acts and slot values in each turn. By treating utterances in isolation, most SLU systems often overlook the semantic context in which a dialog act is expected. The act dependency between turns is non-trivial and yet critical to the identification of the correct semantic representations. Previous works with limited context awareness have exposed the inadequacy of dealing with complexity in multiproned user intents, which are subject to spontaneous change during turn transitions. In this work, we propose to enhance SLU in multi-turn dialogs, employing a context-aware hierarchical BERT fusion Network (CaBERT-SLU) to not only discern context information within a dialog but also jointly identify multiple dialog acts and slots in each utterance. Experimental results show that our approach reaches new state-of-the-art (SOTA) performances in two complicated multi-turn dialogue datasets with considerable improvements compared with previous methods, which only consider single utterances for multiple intents and slot filling.
Spoken Language Understanding (SLU), including intent detection and slot filling, is a core component in human-computer interaction. The natural attributes of the relationship among the two subtasks make higher requirements on fine-grained feature interaction, i.e., the token-level intent features and slot features. Previous works mainly focus on jointly modeling the relationship between the two subtasks with attention-based models, while ignoring the exploration of attention order. In this paper, we propose to replace the conventional attention with our proposed Bilinear attention block and show that the introduced Higher-order Attention Network (HAN) brings improvement for the SLU task. Importantly, we conduct wide analysis to explore the effectiveness brought from the higher-order attention.
Spoken Language Understanding (SLU) is one essential step in building a dialogue system. Due to the expensive cost of obtaining the labeled data, SLU suffers from the data scarcity problem. Therefore, in this paper, we focus on data augmentation for slot filling task in SLU. To achieve that, we aim at generating more diverse data based on existing data. Specifically, we try to exploit the latent language knowledge from pretrained language models by finetuning them. We propose two strategies for finetuning process: value-based and context-based augmentation. Experimental results on two public SLU datasets have shown that compared with existing data augmentation methods, our proposed method can generate more diverse sentences and significantly improve the performance on SLU.
End-to-end spoken language understanding (SLU) systems that process human-human or human-computer interactions are often context independent and process each turn of a conversation independently. Spoken conversations on the other hand, are very much context dependent, and dialog history contains useful information that can improve the processing of each conversational turn. In this paper, we investigate the importance of dialog history and how it can be effectively integrated into end-to-end SLU systems. While processing a spoken utterance, our proposed RNN transducer (RNN-T) based SLU model has access to its dialog history in the form of decoded transcripts and SLU labels of previous turns. We encode the dialog history as BERT embeddings, and use them as an additional input to the SLU model along with the speech features for the current utterance. We evaluate our approach on a recently released spoken dialog data set, the HarperValleyBank corpus. We observe significant improvements: 8% for dialog action and 30% for caller intent recognition tasks, in comparison to a competitive context independent end-to-end baseline system.
Spoken Language Understanding (SLU), a core component of the task-oriented dialogue system, expects a shorter inference latency due to the impatience of humans. Non-autoregressive SLU models clearly increase the inference speed but suffer uncoordinated-slot problems caused by the lack of sequential dependency information among each slot chunk. To gap this shortcoming, in this paper, we propose a novel non-autoregressive SLU model named Layered-Refine Transformer, which contains a Slot Label Generation (SLG) task and a Layered Refine Mechanism (LRM). SLG is defined as generating the next slot label with the token sequence and generated slot labels. With SLG, the non-autoregressive model can efficiently obtain dependency information during training and spend no extra time in inference. LRM predicts the preliminary SLU results from Transformer's middle states and utilizes them to guide the final prediction. Experiments on two public datasets indicate that our model significantly improves SLU performance (1.5\% on Overall accuracy) while substantially speed up (more than 10 times) the inference process over the state-of-the-art baseline.
End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural language processing modules. It attempts to predict intent from speech without using an intermediate ASR module. However, such end-to-end framework suffers from the unavailability of large speech resources with higher acoustic variation in spoken language understanding. In this work, we exploit the scope of the transformer distillation method that is specifically designed for knowledge distillation from a transformer based language model to a transformer based speech model. In this regard, we leverage the reliable and widely used bidirectional encoder representations from transformers (BERT) model as a language model and transfer the knowledge to build an acoustic model for intent classification using the speech. In particular, a multilevel transformer based teacher-student model is designed, and knowledge distillation is performed across attention and hidden sub-layers of different transformer layers of the student and teacher models. We achieve an intent classification accuracy of 99.10% and 88.79% for Fluent speech corpus and ATIS database, respectively. Further, the proposed method demonstrates better performance and robustness in acoustically degraded condition compared to the baseline method.
As more speech processing applications execute locally on edge devices, a set of resource constraints must be considered. In this work we address one of these constraints, namely over-the-network data budgets for transferring models from server to device. We present neural update approaches for release of subsequent speech model generations abiding by a data budget. We detail two architecture-agnostic methods which learn compact representations for transmission to devices. We experimentally validate our techniques with results on two tasks (automatic speech recognition and spoken language understanding) on open source data sets by demonstrating when applied in succession, our budgeted updates outperform comparable model compression baselines by significant margins.
Spoken Language Understanding (SLU) is composed of two subtasks: intent detection (ID) and slot filling (SF). There are two lines of research on SLU. One jointly tackles these two subtasks to improve their prediction accuracy, and the other focuses on the domain-adaptation ability of one of the subtasks. In this paper, we attempt to bridge these two lines of research and propose a joint and domain adaptive approach to SLU. We formulate SLU as a constrained generation task and utilize a dynamic vocabulary based on domain-specific ontology. We conduct experiments on the ASMixed and MTOD datasets and achieve competitive performance with previous state-of-the-art joint models. Besides, results show that our joint model can be effectively adapted to a new domain.