A major focus of recent research in spoken language understanding (SLU) has been on the end-to-end approach where a single model can predict intents directly from speech inputs without intermediate transcripts. However, this approach presents some challenges. First, since speech can be considered as personally identifiable information, in some cases only automatic speech recognition (ASR) transcripts are accessible. Second, intent-labeled speech data is scarce. To address the first challenge, we propose a novel system that can predict intents from flexible types of inputs: speech, ASR transcripts, or both. We demonstrate strong performance for either modality separately, and when both speech and ASR transcripts are available, through system combination, we achieve better results than using a single input modality. To address the second challenge, we leverage a semantically robust pre-trained BERT model and adopt a cross-modal system that co-trains text embeddings and acoustic embeddings in a shared latent space. We further enhance this system by utilizing an acoustic module pre-trained on LibriSpeech and domain-adapting the text module on our target datasets. Our experiments show significant advantages for these pre-training and fine-tuning strategies, resulting in a system that achieves competitive intent-classification performance on Snips SLU and Fluent Speech Commands datasets.
Pohang University of Science and Technology (POSTECH)（浦项科技大学）
We propose two methods to capture relevant history information in a multi-turn dialogue by modeling inter-speaker relationship for spoken language understanding (SLU). Our methods are tailored for and therefore compatible with XLNet, which is a state-of-the-art pretrained model, so we verified our models built on the top of XLNet. In our experiments, all models achieved higher accuracy than state-of-the-art contextual SLU models on two benchmark datasets. Analysis on the results demonstrated that the proposed methods are effective to improve SLU accuracy of XLNet. These methods to identify imp…
A text-independent speaker recognition system relies on successfully encoding speech factors such as vocal pitch, intensity, and timbre to achieve good performance. A majority of such systems are trained and evaluated using spoken voice or everyday conversational voice data. Spoken voice, however, exhibits a limited range of possible speaker dynamics, thus constraining the utility of the derived speaker recognition models. Singing voice, on the other hand, covers a broader range of vocal and ambient factors and can, therefore, be used to evaluate the robustness of a speaker recognition system.…
Current spoken dialogue systems initiate their turns after a long period of silence (700-1000ms), which leads to little real-time feedback, sluggish responses, and an overall stilted conversational flow. Humans typically respond within 200ms and successfully predicting initiation points in advance would allow spoken dialogue agents to do the same. In this work, we predict the lead-time to initiation using prosodic features from a pre-trained speech representation model (wav2vec 1.0) operating on user audio and word features from a pre-trained language model (GPT-2) operating on incremental tra…
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% weigh…
Taiwan International Graduate Program（台湾国际研究生学程）；National Tsing Hua University（台湾清华大学）；Academia Sinica（中央研究院）
We present an overview of the EmotionX 2019 Challenge, held at the 7th International Workshop on Natural Language Processing for Social Media (SocialNLP), in conjunction with IJCAI 2019. The challenge entailed predicting emotions in spoken and chat-based dialogues using augmented EmotionLines datasets. EmotionLines contains two distinct datasets: the first includes excerpts from a US-based TV sitcom episode scripts (Friends) and the second contains online chats (EmotionPush). A total of thirty-six teams registered to participate in the challenge. Eleven of the teams successfully submitted thei…
Johns Hopkins University（约翰斯·霍普金斯大学）；Saarland University（萨尔兰大学）；Higher School of Economics（高等经济学院）；The Institute of Linguistics RAS（俄罗斯科学院语言学研究所）；Mila/McGill University Montreal（米拉/蒙特利尔麦吉尔大学）；Bhim Rao Ambedkar University（比姆·拉奥·安贝德卡尔大学）；ETH Zürich（苏黎世联邦理工学院）；University of Melbourne（墨尔本大学）
While language identification is a fundamental speech and language processing task, for many languages and language families it remains a challenging task. For many low-resource and endangered languages this is in part due to resource availability: where larger datasets exist, they may be single-speaker or have different domains than desired application scenarios, demanding a need for domain and speaker-invariant language identification systems. This year's shared task on robust spoken language identification sought to investigate just this scenario: systems were to be trained on largely singl…
University of Michigan at Ann Arbor（密歇根大学安娜堡分校）；Microsoft（微软）；IBM T. J. Watson Research Center（IBM T. J. 沃森研究中心）
This work focuses on the use of acoustic cues for modeling turn-taking in dyadic spoken dialogues. Previous work has shown that speaker intentions (e.g., asking a question, uttering a backchannel, etc.) can influence turn-taking behavior and are good predictors of turn-transitions in spoken dialogues. However, speaker intentions are not readily available for use by automated systems at run-time; making it difficult to use this information to anticipate a turn-transition. To this end, we propose a multi-task neural approach for predicting turn- transitions and speaker intentions simultaneously.…
Pohang University of Science and Technology (POSTECH)（浦项科技大学）
To capture salient contextual information for spoken language understanding (SLU) of a dialogue, we propose time-aware models that automatically learn the latent time-decay function of the history without a manual time-decay function. We also propose a method to identify and label the current speaker to improve the SLU accuracy. In experiments on the benchmark dataset used in Dialog State Tracking Challenge 4, the proposed models achieved significantly higher F1 scores than the state-of-the-art contextual models. Finally, we analyze the effectiveness of the introduced models in detail. The ana…
Spoken language understanding (SLU) is an essential component in conversational systems. Most SLU component treats each utterance independently, and then the following components aggregate the multi-turn information in the separate phases. In order to avoid error propagation and effectively utilize contexts, prior work leveraged history for contextual SLU. However, the previous model only paid attention to the content in history utterances without considering their temporal information and speaker roles. In the dialogues, the most recent utterances should be more important than the least recen…
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 investi…
In this paper, we address the task of spoken language understanding. We present a method for translating spoken sentences from one language into spoken sentences in another language. Given spectrogram-spectrogram pairs, our model can be trained completely from scratch to translate unseen sentences. Our method consists of a pyramidal-bidirectional recurrent network combined with a convolutional network to output sentence-level spectrograms in the target language. Empirically, our model achieves competitive performance with state-of-the-art methods on multiple languages and can generalize to uns…
Indian Institute of Science（印度科学学院）；Voice and Speech Systems（语音与言语系统公司）
Subjective and objective experiments are conducted to understand the extent to which a speaker's gender influences the acoustics of unvoiced (U) sounds. U segments of utterances are replaced by the corresponding segments of a speaker of opposite gender to prepare modified utterances. Humans are asked to judge if the modified utterance is spoken by one or two speakers. The experiments show that human subjects are unable to distinguish the modified from the original. Thus, listeners are able to identify the U segments irrespective of the gender, which may be based on some speaker-independent inv…
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；Johns Hopkins University（约翰斯·霍普金斯大学）；MIT Lincoln Laboratory（麻省理工学院林肯实验室）
The Multitarget Challenge aims to assess how well current speech technology is able to determine whether or not a recorded utterance was spoken by one of a large number of 'blacklisted' speakers. It is a form of multi-target speaker detection based on real-world telephone conversations. Data recordings are generated from call center customer-agent conversations. Each conversation is represented by a single i-vector. Given a pool of training and development data from non-Blacklist and Blacklist speakers, the task is to measure how accurately one can detect 1) whether a test recording is spoken …
In this thesis, we present a statistical language model for resolving speech repairs, intonational boundaries and discourse markers. Rather than finding the best word interpretation for an acoustic signal, we redefine the speech recognition problem to so that it also identifies the POS tags, discourse markers, speech repairs and intonational phrase endings (a major cue in determining utterance units). Adding these extra elements to the speech recognition problem actually allows it to better predict the words involved, since we are able to make use of the predictions of boundary tones, discours…
University of Avignon（阿维尼翁大学）；University of Le Mans（勒芒大学）；University of Nantes（南特大学）
This work investigates spoken language understanding (SLU) systems in the scenario when the semantic information is extracted directly from the speech signal by means of a single end-to-end neural network model. Two SLU tasks are considered: named entity recognition (NER) and semantic slot filling (SF). For these tasks, in order to improve the model performance, we explore various techniques including speaker adaptation, a modification of the connectionist temporal classification (CTC) training criterion, and sequential pretraining.
University of Pittsburgh（匹兹堡大学）；Adapt Centre, Trinity College Dublin（都柏林圣三一学院适应中心）
Research on human spoken language has shown that speech plays an important role in identifying speaker personality traits. In this work, we propose an approach for identifying speaker personality traits using overlap dynamics in multiparty spoken dialogues. We first define a set of novel features representing the overlap dynamics of each speaker. We then investigate the impact of speaker personality traits on these features using ANOVA tests. We find that features of overlap dynamics significantly vary for speakers with different levels of both Extraversion and Conscientiousness. Finally, we f…
LTCI, Telecom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信学院LTCI实验室）；IBM GBS France（IBM全球企业服务法国分部）
While being an essential component of spoken language, fillers (e.g."um" or "uh") often remain overlooked in Spoken Language Understanding (SLU) tasks. We explore the possibility of representing them with deep contextualised embeddings, showing improvements on modelling spoken language and two downstream tasks - predicting a speaker's stance and expressed confidence.
Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking
Language Technology Lab, University of Cambridge（剑桥大学语言技术实验室）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑技术大学计算、信息与技术学院）；Independent Researcher（独立研究员）
This paper describes a system that leads us to believe in the feasibility of constructing natural spoken dialogue systems in task-oriented domains. It specifically addresses the issue of robust interpretation of speech in the presence of recognition errors. Robustness is achieved by a combination of statistical error post-correction, syntactically- and semantically-driven robust parsing, and extensive use of the dialogue context. We present an evaluation of the system using time-to-completion and the quality of the final solution that suggests that most native speakers of English can use the s…
In this paper, we have introduced and evaluated intonation based feature for scoring the English speech of nonnative English speakers in Indian context. For this, we created an automated spoken English scoring engine to learn from the manual evaluation of spoken English. This involved using an existing Automatic Speech Recognition (ASR) engine to convert the speech to text. Thereafter, macro features like accuracy, fluency and prosodic features were used to build a scoring model. In the process, we introduced SimIntonation, short for similarity between spoken intonation pattern and "ideal" i.e…
