A lot of work has been done to build text-based language models for performing different NLP tasks, but not much research has been done in the case of audio-based language models. This paper proposes a Convolutional Autoencoder based neural architecture to model syntactically and semantically adequate contextualized representations of varying length spoken words. The use of such representations can not only lead to great advances in the audio-based NLP tasks but can also curtail the loss of information like tone, expression, accent, etc while converting speech to text to perform these tasks. The performance of the proposed model is validated by (1) examining the generated vector space, and (2) evaluating its performance on three benchmark datasets for measuring word similarities, against existing widely used text-based language models that are trained on the transcriptions. The proposed model was able to demonstrate its robustness when compared to the other two language-based models.
Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech recognizer (ASR) is concerned. Therefore, this paper focuses on making contextualized representations more ASR-robust. We propose a novel confusion-aware fine-tuning method to mitigate the impact of ASR errors to pre-trained LMs. Specifically, we fine-tune LMs to produce similar representations for acoustically confusable words that are obtained from word conf…
Spoken conversational question answering (SCQA) requires machines to model complex dialogue flow given the speech utterances and text corpora. Different from traditional text question answering (QA) tasks, SCQA involves audio signal processing, passage comprehension, and contextual understanding. However, ASR systems introduce unexpected noisy signals to the transcriptions, which result in performance degradation on SCQA. To overcome the problem, we propose CADNet, a novel contextualized attention-based distillation approach, which applies both cross-attention and self-attention to obtain ASR-…
National Taiwan University of Science and Technology（台湾科技大学）
In a spoken multiple-choice question answering (SMCQA) task, given a passage, a question, and multiple choices all in the form of speech, the machine needs to pick the correct choice to answer the question. While the audio could contain useful cues for SMCQA, usually only the auto-transcribed text is utilized in system development. Thanks to the large-scaled pre-trained language representation models, such as the bidirectional encoder representations from transformers (BERT), systems with only auto-transcribed text can still achieve a certain level of performance. However, previous studies hav…
Pre-trained language models have achieved huge improvement on many NLP tasks. However, these methods are usually designed for written text, so they do not consider the properties of spoken language. Therefore, this paper aims at generalizing the idea of language model pre-training to lattices generated by recognition systems. We propose a framework that trains neural lattice language models to provide contextualized representations for spoken language understanding tasks. The proposed two-stage pre-training approach reduces the demands of speech data and has better efficiency. Experiments on i…
Word Error Rate (WER) has been the predominant metric used to evaluate the performance of automatic speech recognition (ASR) systems. However, WER is sometimes not a good indicator for downstream Natural Language Understanding (NLU) tasks, such as intent recognition, slot filling, and semantic parsing in task-oriented dialog systems. This is because WER takes into consideration only literal correctness instead of semantic correctness, the latter of which is typically more important for these downstream tasks. In this study, we propose a novel Semantic Distance (SemDist) measure as an alternati…
While Word2Vec represents words (in text) as vectors carrying semantic information, audio Word2Vec was shown to be able to represent signal segments of spoken words as vectors carrying phonetic structure information. Audio Word2Vec can be trained in an unsupervised way from an unlabeled corpus, except the word boundaries are needed. In this paper, we extend audio Word2Vec from word-level to utterance-level by proposing a new segmental audio Word2Vec, in which unsupervised spoken word boundary segmentation and audio Word2Vec are jointly learned and mutually enhanced, so an utterance can be dire…
Language model pre-training has shown promising results in various downstream tasks. In this context, we introduce a cross-modal pre-trained language model, called Speech-Text BERT (ST-BERT), to tackle end-to-end spoken language understanding (E2E SLU) tasks. Taking phoneme posterior and subword-level text as an input, ST-BERT learns a contextualized cross-modal alignment via our two proposed pre-training tasks: Cross-modal Masked Language Modeling (CM-MLM) and Cross-modal Conditioned Language Modeling (CM-CLM). Experimental results on three benchmarks present that our approach is effective fo…
Data scarcity is one of the main obstacles of domain adaptation in spoken language understanding (SLU) due to the high cost of creating manually tagged SLU datasets. Recent works in neural text generative models, particularly latent variable models such as variational autoencoder (VAE), have shown promising results in regards to generating plausible and natural sentences. In this paper, we propose a novel generative architecture which leverages the generative power of latent variable models to jointly synthesize fully annotated utterances. Our experiments show that existing SLU models trained …
Indian Association for the Cultivation of Science（印度科学培育协会）；Ashoka University（阿育王大学）；Indian Institute of Technology Kharagpur（印度理工学院卡哈拉格普尔分校）
Topic modeling has emerged as a dominant method for exploring large document collections. Recent approaches to topic modeling use large contextualized language models and variational autoencoders. In this paper, we propose a negative sampling mechanism for a contextualized topic model to improve the quality of the generated topics. In particular, during model training, we perturb the generated document-topic vector and use a triplet loss to encourage the document reconstructed from the correct document-topic vector to be similar to the input document and dissimilar to the document reconstructe…
Word embeddings such as ELMo have recently been shown to model word semantics with greater efficacy through contextualized learning on large-scale language corpora, resulting in significant improvement in state of the art across many natural language tasks. In this work we integrate acoustic information into contextualized lexical embeddings through the addition of multimodal inputs to a pretrained bidirectional language model. The language model is trained on spoken language that includes text and audio modalities. The resulting representations from this model are multimodal and contain paral…
User interaction with voice-powered agents generates large amounts of unlabeled utterances. In this paper, we explore techniques to efficiently transfer the knowledge from these unlabeled utterances to improve model performance on Spoken Language Understanding (SLU) tasks. We use Embeddings from Language Model (ELMo) to take advantage of unlabeled data by learning contextualized word representations. Additionally, we propose ELMo-Light (ELMoL), a faster and simpler unsupervised pre-training method for SLU. Our findings suggest unsupervised pre-training on a large corpora of unlabeled utterance…
Sigma Technologies S.L.U.（西格玛技术有限公司）；Universidad Politécnica de Madrid（马德里理工大学）
The fast increase of web services and mobile apps, which collect personal data from users, increases the risk that their privacy may be severely compromised. In particular, the increasing variety of spoken language interfaces and voice assistants empowered by the vertiginous breakthroughs in Deep Learning are prompting important concerns in the European Union to preserve speech data privacy. For instance, an attacker can record speech from users and impersonate them to get access to systems requiring voice identification. Hacking speaker profiles from users is also possible by means of existin…
End-to-end approaches open a new way for more accurate and efficient spoken language understanding (SLU) systems by alleviating the drawbacks of traditional pipeline systems. Previous works exploit textual information for an SLU model via pre-training with automatic speech recognition or fine-tuning with knowledge distillation. To utilize textual information more effectively, this work proposes a two-stage textual knowledge distillation method that matches utterance-level representations and predicted logits of two modalities during pre-training and fine-tuning, sequentially. We use vq-wav2vec…
Institute for Language, Cognition and Computation（语言、认知与计算研究所）；University of Edinburgh（爱丁堡大学）
In this work, we study the representation space of contextualized embeddings and gain insight into the hidden topology of large language models. We show there exists a network of latent states that summarize linguistic properties of contextualized representations. Instead of seeking alignments to existing well-defined annotations, we infer this latent network in a fully unsupervised way using a structured variational autoencoder. The induced states not only serve as anchors that mark the topology (neighbors and connectivity) of the representation manifold but also reveal the internal mechanism…
Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey desired information. Traditional template-based generators can produce sentences with all necessary information, but these sentences are not sufficiently diverse. With RNN-based models, the diversity of the generated sentences can be high, however, in the process some information is lost. In this work, we improve an RNN-based generator by considering latent inform…
University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；University of British Columbia（不列颠哥伦比亚大学）；Indiana University Bloomington（印第安纳大学伯明顿分校）；Newcastle University（纽卡斯尔大学）；Max Planck Institute for Human Cognitive and Brain Sciences（马克斯·普朗克人类认知与脑科学研究所）
Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding. This study tackles the unsupervised learning of semantic representations for spoken utterances. Through converting speech signals into hidden units generated from acoustic unit discovery, we propose WavEmbed, a multimodal sequential autoencoder that predicts hidden units from a dense representation of speech. Secondly, we also propose S-HuBERT to induce meaning through knowledge distillation, in which a sentence embeddi…
Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds of a small number of exemplar words without hearing a large amount of data. We initiate some preliminary work in this direction in this paper. Audio Word2Vec is used to obtain embeddings of spoken words which carry phonetic information extracted from the signals. An autoencoder is used to generate embeddings of text words based on the articulatory features f…
Given the strong results of self-supervised models on various tasks, there have been surprisingly few studies exploring self-supervised representations for acoustic word embeddings (AWE), fixed-dimensional vectors representing variable-length spoken word segments. In this work, we study several pre-trained models and pooling methods for constructing AWEs with self-supervised representations. Owing to the contextualized nature of self-supervised representations, we hypothesize that simple pooling methods, such as averaging, might already be useful for constructing AWEs. When evaluating on a sta…
Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds (or phonetic structures) of a small number of exemplar words, and "generalize" such knowledge to other words without hearing a large amount of data. We initiate some preliminary work in this direction. Audio Word2Vec is used to learn the phonetic structures from spoken words (signal segments), while another autoencoder is used to learn the phonetic structure…
A vast majority of the world's 7,000 spoken languages are predicted to become extinct within this century, including the endangered language of Ladin from the Italian Alps. Linguists who work to preserve a language's phonetic and phonological structure can spend hours transcribing each minute of speech from native speakers. To address this problem in the context of Ladin, our paper presents the first analysis of speech representations and machine learning models for classifying 32 phonemes of Ladin. We experimented with a novel dataset of the Fascian dialect of Ladin, collected from native spe…
rinna Co., Ltd.（Rinna株式会社）；Nagoya Institute of Technology（名古屋工业大学）
The recent text-to-speech (TTS) has achieved quality comparable to that of humans; however, its application in spoken dialogue has not been widely studied. This study aims to realize a TTS that closely resembles human dialogue. First, we record and transcribe actual spontaneous dialogues. Then, the proposed dialogue TTS is trained in two stages: first stage, variational autoencoder (VAE)-VITS or Gaussian mixture variational autoencoder (GMVAE)-VITS is trained, which introduces an utterance-level latent variable into variational inference with adversarial learning for end-to-end text-to-speech …
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；St Michael’s Hospital（圣迈克尔医院）
Tone is a prosodic feature used to distinguish words in many languages, some of which are endangered and scarcely documented. In this work, we use unsupervised representation learning to identify probable clusters of syllables that share the same phonemic tone. Our method extracts the pitch for each syllable, then trains a convolutional autoencoder to learn a low dimensional representation for each contour. We then apply the mean shift algorithm to cluster tones in high-density regions of the latent space. Furthermore, by feeding the centers of each cluster into the decoder, we produce a proto…
Audio Word2Vec offers vector representations of fixed dimensionality for variable-length audio segments using Sequence-to-sequence Autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of the audio segments to a good degree, with real world applications such as query-by-example Spoken Term Detection (STD). This paper examines the capability of language transfer of Audio Word2Vec. We train SA from one language (source language) and use it to extract the vector representation of the audio segments of another language (target language). We found t…
We present a framework for building speech-to-text translation (ST) systems using only monolingual speech and text corpora, in other words, speech utterances from a source language and independent text from a target language. As opposed to traditional cascaded systems and end-to-end architectures, our system does not require any labeled data (i.e., transcribed source audio or parallel source and target text corpora) during training, making it especially applicable to language pairs with very few or even zero bilingual resources. The framework initializes the ST system with a cross-modal biling…
