(Part of the abstract) In this thesis, we investigate the use of unsupervised spoken term discovery in tackling this problem. Unsupervised spoken term discovery aims to discover topic-related terminologies in a speech without knowing the phonetic properties of the language and content. It can be further divided into two parts: Acoustic segment modelling (ASM) and unsupervised pattern discovery. ASM learns the phonetic structures of zero-resource language audio with no phonetic knowledge available, generating self-derived "phonemes". The audio are labelled with these "phonemes" to obtain "phoneme" sequences. Unsupervised pattern discovery searches for repetitive patterns in the "phoneme" sequences. The discovered patterns can be grouped to determine the keywords of the audio. Multilingual neural network with bottleneck layer is used for feature extraction. Experiments show that bottleneck features facilitate the training of ASM compared to conventional features such as MFCC. The unsupervised spoken term discovery system is experimented with online lectures covering different topics by different speakers. It is shown that the system learns the phonetic information of the language and can discover frequent spoken terms that align with text transcription. By using information retrieval technology such as word embedding and TFIDF, it is shown that the discovered keywords can be further used for topic comparison.
University of California Los Angeles（加州大学洛杉矶分校）；PAII Inc.（PAII公司）
This paper describes the SPAPL system for the INTERSPEECH 2021 Challenge: Shared Task on Automatic Speech Recognition for Non-Native Children's Speech in German. ~ 5 hours of transcribed data and ~ 60 hours of untranscribed data are provided to develop a German ASR system for children. For the training of the transcribed data, we propose a non-speech state discriminative loss (NSDL) to mitigate the influence of long-duration non-speech segments within speech utterances. In order to explore the use of the untranscribed data, various approaches are implemented and combined together to incrementa…
There is growing interest in models that can learn from unlabelled speech paired with visual context. This setting is relevant for low-resource speech processing, robotics, and human language acquisition research. Here we study how a visually grounded speech model, trained on images of scenes paired with spoken captions, captures aspects of semantics. We use an external image tagger to generate soft text labels from images, which serve as targets for a neural model that maps untranscribed speech to (semantic) keyword labels. We introduce a newly collected data set of human semantic relevance j…
Stanford University（斯坦福大学）；ARC Centre of Excellence for the Dynamics of Language（ARC语言动态卓越中心）；University of Groningen（格罗宁根大学）；University of Queensland（昆士兰大学）；University of Melbourne（墨尔本大学）；Australian National University（澳大利亚国立大学）；University of Sydney（悉尼大学）；University of Freiburg（弗莱堡大学）
Pre-trained speech representations like wav2vec 2.0 are a powerful tool for automatic speech recognition (ASR). Yet many endangered languages lack sufficient data for pre-training such models, or are predominantly oral vernaculars without a standardised writing system, precluding fine-tuning. Query-by-example spoken term detection (QbE-STD) offers an alternative for iteratively indexing untranscribed speech corpora by locating spoken query terms. Using data from 7 Australian Aboriginal languages and a regional variety of Dutch, all of which are endangered or vulnerable, we show that QbE-STD ca…
In this paper, we explore the learning of neural network embeddings for natural images and speech waveforms describing the content of those images. These embeddings are learned directly from the waveforms without the use of linguistic transcriptions or conventional speech recognition technology. While prior work has investigated this setting in the monolingual case using English speech data, this work represents the first effort to apply these techniques to languages beyond English. Using spoken captions collected in English and Hindi, we show that the same model architecture can be successful…
In this paper, we propose a novel architecture for direct extractive speech-to-speech summarization, ESSumm, which is an unsupervised model without dependence on intermediate transcribed text. Different from previous methods with text presentation, we are aimed at generating a summary directly from speech without transcription. First, a set of smaller speech segments are extracted based on speech signal's acoustic features. For each candidate speech segment, a distance-based summarization confidence score is designed for latent speech representation measure. Specifically, we leverage the off-t…
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
In this paper, we proposed Adapitch, a multi-speaker TTS method that makes adaptation of the supervised module with untranscribed data. We design two self supervised modules to train the text encoder and mel decoder separately with untranscribed data to enhance the representation of text and mel. To better handle the prosody information in a synthesized voice, a supervised TTS module is designed conditioned on content disentangling of pitch, text, and speaker. The training phase was separated into two parts, pretrained and fixed the text encoder and mel decoder with unsupervised mode, then the…
University of Washington（华盛顿大学）；Google Research（谷歌研究院）
Systems that can associate images with their spoken audio captions are an important step towards visually grounded language learning. We describe a scalable method to automatically generate diverse audio for image captioning datasets. This supports pretraining deep networks for encoding both audio and images, which we do via a dual encoder that learns to align latent representations from both modalities. We show that a masked margin softmax loss for such models is superior to the standard triplet loss. We fine-tune these models on the Flickr8k Audio Captions Corpus and obtain state-of-the-art …
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN（理化学研究所）
In this paper, we explore a method for training speech-to-speech translation tasks without any transcription or linguistic supervision. Our proposed method consists of two steps: First, we train and generate discrete representation with unsupervised term discovery with a discrete quantized autoencoder. Second, we train a sequence-to-sequence model that directly maps the source language speech to the target language's discrete representation. Our proposed method can directly generate target speech without any auxiliary or pre-training steps with a source or target transcription. To the best of …
The present study tackles the problem of automatically discovering spoken keywords from untranscribed audio archives without requiring word-by-word speech transcription by automatic speech recognition (ASR) technology. The problem is of practical significance in many applications of speech analytics, including those concerning low-resource languages, and large amount of multilingual and multi-genre data. We propose a two-stage approach, which comprises unsupervised acoustic modeling and decoding, followed by pattern mining in acoustic unit sequences. The whole process starts by deriving and mo…
(Short version of Abstract) This thesis describes an investigation on unsupervised acoustic modeling (UAM) for automatic speech recognition (ASR) in the zero-resource scenario, where only untranscribed speech data is assumed to be available. UAM is not only important in addressing the general problem of data scarcity in ASR technology development but also essential to many non-mainstream applications, for examples, language protection, language acquisition and pathological speech assessment. The present study is focused on two research problems. The first problem concerns unsupervised discover…
Spoken term discovery from untranscribed speech audio could be achieved via a two-stage process. In the first stage, the unlabelled speech is decoded into a sequence of subword units that are learned and modelled in an unsupervised manner. In the second stage, partial sequence matching and clustering are performed on the decoded subword sequences, resulting in a set of discovered words or phrases. A limitation of this approach is that the results of subword decoding could be erroneous, and the errors would impact the subsequent steps. While Siamese/Triplet network is one approach to learn segm…
Keyword localisation is the task of finding where in a speech utterance a given query keyword occurs. We investigate to what extent keyword localisation is possible using a visually grounded speech (VGS) model. VGS models are trained on unlabelled images paired with spoken captions. These models are therefore self-supervised -- trained without any explicit textual label or location information. To obtain training targets, we first tag training images with soft text labels using a pretrained visual classifier with a fixed vocabulary. This enables a VGS model to predict the presence of a written…
Facebook AI Research（Facebook人工智能研究院）；EHESS（社会科学高等学院）；CNRS（法国国家科学研究中心）；INRIA（法国国家信息与自动化研究所）
We introduce a new unsupervised task, spoken language modeling: the learning of linguistic representations from raw audio signals without any labels, along with the Zero Resource Speech Benchmark 2021: a suite of 4 black-box, zero-shot metrics probing for the quality of the learned models at 4 linguistic levels: phonetics, lexicon, syntax and semantics. We present the results and analyses of a composite baseline made of the concatenation of three unsupervised systems: self-supervised contrastive representation learning (CPC), clustering (k-means) and language modeling (LSTM or BERT). The langu…
This research addresses the problem of acoustic modeling of low-resource languages for which transcribed training data is absent. The goal is to learn robust frame-level feature representations that can be used to identify and distinguish subword-level speech units. The proposed feature representations comprise various types of multilingual bottleneck features (BNFs) that are obtained via multi-task learning of deep neural networks (MTL-DNN). One of the key problems is how to acquire high-quality frame labels for untranscribed training data to facilitate supervised DNN training. It is shown th…
In the domain of unsupervised learning most work on speech has focused on discovering low-level constructs such as phoneme inventories or word-like units. In contrast, for written language, where there is a large body of work on unsupervised induction of semantic representations of words, whole sentences and longer texts. In this study we examine the challenges of adapting these approaches from written to spoken language. We conjecture that unsupervised learning of the semantics of spoken language becomes feasible if we abstract from the surface variability. We simulate this setting with a dat…
Institute for Natural Language Processing, University of Stuttgart（斯图加特大学自然语言处理研究所）
In this paper, we investigate the use of adversarial learning for unsupervised adaptation to unseen recording conditions, more specifically, single microphone far-field speech. We adapt neural networks based acoustic models trained with close-talk clean speech to the new recording conditions using untranscribed adaptation data. Our experimental results on Italian SPEECON data set show that our proposed method achieves 19.8% relative word error rate (WER) reduction compared to the unadapted models. Furthermore, this adaptation method is beneficial even when performed on data from another langua…
Unsupervised spoken term discovery consists of two tasks: finding the acoustic segment boundaries and labeling acoustically similar segments with the same labels. We perform segmentation based on the assumption that the frame feature vectors are more similar within a segment than across the segments. Therefore, for strong segmentation performance, it is crucial that the features represent the phonetic properties of a frame more than other factors of variability. We achieve this via a self-expressing autoencoder framework. It consists of a single encoder and two decoders with shared weights. Th…
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…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection of texts written in that language without access to any transcribed speech. Developing such a system can significantly improve the availability of speech technology to languages without a large amount of parallel speech and text data. This paper proposes an unsupervised TTS system based on an alignment module that outputs pseudo-text and another synthesis mo…
Recently, sequence-to-sequence models with attention have been successfully applied in Text-to-speech (TTS). These models can generate near-human speech with a large accurately-transcribed speech corpus. However, preparing such a large data-set is both expensive and laborious. To alleviate the problem of heavy data demand, we propose a novel unsupervised pre-training mechanism in this paper. Specifically, we first use Vector-quantization Variational-Autoencoder (VQ-VAE) to ex-tract the unsupervised linguistic units from large-scale, publicly found, and untranscribed speech. We then pre-train t…
The Sparsespeech model is an unsupervised acoustic model that can generate discrete pseudo-labels for untranscribed speech. We extend the Sparsespeech model to allow for sampling over a random discrete variable, yielding pseudo-posteriorgrams. The degree of sparsity in this posteriorgram can be fully controlled after the model has been trained. We use the Gumbel-Softmax trick to approximately sample from a discrete distribution in the neural network and this allows us to train the network efficiently with standard backpropagation. The new and improved model is trained and evaluated on the Libr…
National Institute of Informatics（国立信息学研究所）；Unversity of Edinburgh（爱丁堡大学）
This paper proposes a new architecture for speaker adaptation of multi-speaker neural-network speech synthesis systems, in which an unseen speaker's voice can be built using a relatively small amount of speech data without transcriptions. This is sometimes called "unsupervised speaker adaptation". More specifically, we concatenate the layers to the audio inputs when performing unsupervised speaker adaptation while we concatenate them to the text inputs when synthesizing speech from text. Two new training schemes for the new architecture are also proposed in this paper. These training schemes a…
National Institute of Information and Communications Technology（日本国立信息与通信技术研究所）；Research Center for Information Technology Innovation, Academic Sinica（中央研究院资讯科技创新研究中心）
Due to the mismatch of statistical distributions of acoustic speech between training and testing sets, the performance of spoken language identification (SLID) could be drastically degraded. In this paper, we propose an unsupervised neural adaptation model to deal with the distribution mismatch problem for SLID. In our model, we explicitly formulate the adaptation as to reduce the distribution discrepancy on both feature and classifier for training and testing data sets. Moreover, inspired by the strong power of the optimal transport (OT) to measure distribution discrepancy, a Wasserstein dist…
This paper adapts a StyleGAN model for speech generation with minimal or no conditioning on text. StyleGAN is a multi-scale convolutional GAN capable of hierarchically capturing data structure and latent variation on multiple spatial (or temporal) levels. The model has previously achieved impressive results on facial image generation, and it is appealing to audio applications due to similar multi-level structures present in the data. In this paper, we train a StyleGAN to generate mel-frequency spectrograms on the Speech Commands dataset, which contains spoken digits uttered by multiple speaker…
Carnegie Mellon University（卡内基梅隆大学）；National Taiwan University（台湾大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Meta AI
Spoken language understanding (SLU) is a task aiming to extract high-level semantics from spoken utterances. Previous works have investigated the use of speech self-supervised models and textual pre-trained models, which have shown reasonable improvements to various SLU tasks. However, because of the mismatched modalities between speech signals and text tokens, previous methods usually need complex designs of the frameworks. This work proposes a simple yet efficient unsupervised paradigm that connects speech and textual pre-trained models, resulting in an unsupervised speech-to-semantic pre-tr…
Neural text-to-speech (TTS) models can synthesize natural human speech when trained on large amounts of transcribed speech. However, collecting such large-scale transcribed data is expensive. This paper proposes an unsupervised pre-training method for a sequence-to-sequence TTS model by leveraging large untranscribed speech data. With our pre-training, we can remarkably reduce the amount of paired transcribed data required to train the model for the target downstream TTS task. The main idea is to pre-train the model to reconstruct de-warped mel-spectrograms from warped ones, which may allow th…
Bar-Ilan University（巴伊兰大学）；Facebook AI Research（脸书人工智能研究院）
We propose a self-supervised representation learning model for the task of unsupervised phoneme boundary detection. The model is a convolutional neural network that operates directly on the raw waveform. It is optimized to identify spectral changes in the signal using the Noise-Contrastive Estimation principle. At test time, a peak detection algorithm is applied over the model outputs to produce the final boundaries. As such, the proposed model is trained in a fully unsupervised manner with no manual annotations in the form of target boundaries nor phonetic transcriptions. We compare the propo…
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…
This study tackles unsupervised subword modeling in the zero-resource scenario, learning frame-level speech representation that is phonetically discriminative and speaker-invariant, using only untranscribed speech for target languages. Frame label acquisition is an essential step in solving this problem. High quality frame labels should be in good consistency with golden transcriptions and robust to speaker variation. We propose to improve frame label acquisition in our previously adopted deep neural network-bottleneck feature (DNN-BNF) architecture by applying the factorized hierarchical vari…
The scarcity of training data and the large speaker variation in dysarthric speech lead to poor accuracy and poor speaker generalization of spoken language understanding systems for dysarthric speech. Through work on the speech features, we focus on improving the model generalization ability with limited dysarthric data. Factorized Hierarchical Variational Auto-Encoders (FHVAE) trained unsupervisedly have shown their advantage in disentangling content and speaker representations. Earlier work showed that the dysarthria shows in both feature vectors. Here, we add adversarial training to bridge …
We consider the task of multimodal one-shot speech-image matching. An agent is shown a picture along with a spoken word describing the object in the picture, e.g. cookie, broccoli and ice-cream. After observing one paired speech-image example per class, it is shown a new set of unseen pictures, and asked to pick the "ice-cream". Previous work attempted to tackle this problem using transfer learning: supervised models are trained on labelled background data not containing any of the one-shot classes. Here we compare transfer learning to unsupervised models trained on unlabelled in-domain data. …
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…
Computer Science and Artificial Intelligence Laboratory（计算机科学与人工智能实验室）；Massachusetts Institute of Technology（麻省理工学院）
Recent research has shown that word embedding spaces learned from text corpora of different languages can be aligned without any parallel data supervision. Inspired by the success in unsupervised cross-lingual word embeddings, in this paper we target learning a cross-modal alignment between the embedding spaces of speech and text learned from corpora of their respective modalities in an unsupervised fashion. The proposed framework learns the individual speech and text embedding spaces, and attempts to align the two spaces via adversarial training, followed by a refinement procedure. We show ho…
University of California, Los Angeles（加州大学洛杉矶分校）；Meta AI；National Taiwan University（国立台湾大学）
Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM) systems achieve state-of-the-art results on semantic spoken language tasks by utilizing rich semantic representations from the LLM. These systems come at the cost of labeled audio transcriptions, which is expensive and time-consuming to obtain. We propose a task-agnostic unsupervised way of incorporating semantic information from LLMs into self-supervised speech encoders witho…
State-of-the-art spoken language identification (LID) systems, which are based on end-to-end deep neural networks, have shown remarkable success not only in discriminating between distant languages but also between closely-related languages or even different spoken varieties of the same language. However, it is still unclear to what extent neural LID models generalize to speech samples with different acoustic conditions due to domain shift. In this paper, we present a set of experiments to investigate the impact of domain mismatch on the performance of neural LID systems for a subset of six Sl…
This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery is formulated as a pipeline of phonetically discriminative feature learning and unit inference. One major difficulty in robust unsupervised feature learning is dealing with speaker variation. Here the robustness towards speaker variation is achieved by applying adversarial training and FHVAE based disentangled speech representation learning. A comparison of…
Deep neural networks have largely demonstrated their ability to perform automated speech recognition (ASR) by extracting meaningful features from input audio frames. Such features, however, may consist not only of information about the spoken language content, but also may contain information about unnecessary contexts such as background noise and sounds or speaker identity, accent, or protected attributes. Such information can directly harm generalization performance, by introducing spurious correlations between the spoken words and the context in which such words were spoken. In this work, w…
We introduce "Unspeech" embeddings, which are based on unsupervised learning of context feature representations for spoken language. The embeddings were trained on up to 9500 hours of crawled English speech data without transcriptions or speaker information, by using a straightforward learning objective based on context and non-context discrimination with negative sampling. We use a Siamese convolutional neural network architecture to train Unspeech embeddings and evaluate them on speaker comparison, utterance clustering and as a context feature in TDNN-HMM acoustic models trained on TED-LIUM,…
Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U, short for wav2vec Unsupervised, a method to train speech recognition models without any labeled data. We leverage self-supervised speech representations to segment unlabeled audio and learn a mapping from these representations to phonemes via adversarial training. The right representations are key to the success of our method. Compared to the best previous unsu…
National Institute of Informatics（国立信息学研究所）；KTH Royal Institute of Technology（KTH皇家理工学院）；University of Edinburgh（爱丁堡大学）
Generating versatile and appropriate synthetic speech requires control over the output expression separate from the spoken text. Important non-textual speech variation is seldom annotated, in which case output control must be learned in an unsupervised fashion. In this paper, we perform an in-depth study of methods for unsupervised learning of control in statistical speech synthesis. For example, we show that popular unsupervised training heuristics can be interpreted as variational inference in certain autoencoder models. We additionally connect these models to VQ-VAEs, another, recently-prop…
Unsupervised spoken term discovery (UTD) aims at finding recurring segments of speech from a corpus of acoustic speech data. One potential approach to this problem is to use dynamic time warping (DTW) to find well-aligning patterns from the speech data. However, automatic selection of initial candidate segments for the DTW-alignment and detection of "sufficiently good" alignments among those require some type of pre-defined criteria, often operationalized as threshold parameters for pair-wise distance metrics between signal representations. In the existing UTD systems, the optimal hyperparamet…
We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through conditioning on past frames and predicting information about future frames. Whereas Mockingjay is designed to predict the current frame through jointly conditioning on both past and future contexts. The Mockingjay representation improves performance for a wide range of downstream tasks, including phoneme classification, speaker recognition, and sentiment classification on spok…
Probing phoneme, language and speaker information in unsupervised speech representations
Cognitive Machine Learning (ENS–CNRS–EHESS–INRIA–PSL Research University)（认知机器学习实验室（巴黎高等师范学院-法国国家科学研究中心-法国高等社会科学研究院-法国国家信息与自动化研究所-巴黎文理研究大学））；Université de Paris Cité（巴黎西岱大学）；CNRS（法国国家科学研究中心）；Meta AI Research（Meta人工智能研究院）
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…
University of Toronto（多伦多大学）；École Normale Supérieure（巴黎高等师范学院）；Inria（法国国家信息与自动化研究所）；École des Hautes Études en Sciences Sociales（巴黎高等社会科学研究学院）；Meta AI
Recent progress in self-supervised or unsupervised machine learning has opened the possibility of building a full speech processing system from raw audio without using any textual representations or expert labels such as phonemes, dictionaries or parse trees. The contribution of the Zero Resource Speech Challenge series since 2015 has been to break down this long-term objective into four well-defined tasks -- Acoustic Unit Discovery, Spoken Term Discovery, Discrete Resynthesis, and Spoken Language Modeling -- and introduce associated metrics and benchmarks enabling model comparison and cumulat…
Discovering speaker independent acoustic units purely from spoken input is known to be a hard problem. In this work we propose an unsupervised speaker normalization technique prior to unit discovery. It is based on separating speaker related from content induced variations in a speech signal with an adversarial contrastive predictive coding approach. This technique does neither require transcribed speech nor speaker labels, and, furthermore, can be trained in a multilingual fashion, thus achieving speaker normalization even if only few unlabeled data is available from the target language. The …
