We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics to automatically evaluate the learned representations at acoustic and linguistic levels for both encoding and generation. We set up baseline systems consisting of a discrete speech encoder (returning pseudo-text units), a generative language model (trained on pseudo-text), and a speech decoder (generating a waveform from pseudo-text) all trained without supervision and validate the proposed metrics with human evaluation. Across 3 speech encoders (CPC, wav2vec 2.0, HuBERT), we find that the number of discrete units (50, 100, or 200) matters in a task-dependent and encoder-dependent way, and that some combinations approach text-based systems.
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…
Embedding audio signal segments into vectors with fixed dimensionality is attractive because all following processing will be easier and more efficient, for example modeling, classifying or indexing. Audio Word2Vec previously proposed was shown to be able to represent audio segments for spoken words as such vectors carrying information about the phonetic structures of the signal segments. However, each linguistic unit (word, syllable, phoneme in text form) corresponds to unlimited number of audio segments with vector representations inevitably spread over the embedding space, which causes some…
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…
University of Zurich（苏黎世大学）；University of Edinburgh（爱丁堡大学）
For real-life applications, it is crucial that end-to-end spoken language translation models perform well on continuous audio, without relying on human-supplied segmentation. For online spoken language translation, where models need to start translating before the full utterance is spoken, most previous work has ignored the segmentation problem. In this paper, we compare various methods for improving models' robustness towards segmentation errors and different segmentation strategies in both offline and online settings and report results on translation quality, flicker and delay. Our findings …
Spoken language understanding system is traditionally designed as a pipeline of a number of components. First, the audio signal is processed by an automatic speech recognizer for transcription or n-best hypotheses. With the recognition results, a natural language understanding system classifies the text to structured data as domain, intent and slots for down-streaming consumers, such as dialog system, hands-free applications. These components are usually developed and optimized independently. In this paper, we present our study on an end-to-end learning system for spoken language understanding…
IIIT Delhi（德里印度理工学院）；BITS Pilani（皮拉尼比尔拉科学技术学院）；Adobe（奥多比公司）；SUNY at Buffalo（纽约州立大学布法罗分校）；Second Language Testing Inc（第二语言测试公司）；National University of Singapore（新加坡国立大学）
While there has been significant progress towards modelling coherence in written discourse, the work in modelling spoken discourse coherence has been quite limited. Unlike the coherence in text, coherence in spoken discourse is also dependent on the prosodic and acoustic patterns in speech. In this paper, we model coherence in spoken discourse with audio-based coherence models. We perform experiments with four coherence-related tasks with spoken discourses. In our experiments, we evaluate machine-generated speech against the speech delivered by expert human speakers. We also compare the spoken…
We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence level. Formulated as an audio-linguistic multitask learning problem, our encoder-decoder model simultaneously reconstructs acoustic and natural language features from audio. Our results show that spoken sentence embeddings outperform phoneme and word-level baselines on speech recognition and emotion recognition tasks. Ablation studies show that our embeddings c…
Institute for Language, Cognition, and Computation（语言、认知与计算研究所）；Centre for Speech Technology Research（语音技术研究中心）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
Recent work on unsupervised term discovery (UTD) aims to identify and cluster repeated word-like units from audio alone. These systems are promising for some very low-resource languages where transcribed audio is unavailable, or where no written form of the language exists. However, in some cases it may still be feasible (e.g., through crowdsourcing) to obtain (possibly noisy) text translations of the audio. If so, this information could be used as a source of side information to improve UTD. Here, we present a simple method for rescoring the output of a UTD system using text translations, and…
In this paper, we present a novel deep multimodal framework to predict human emotions based on sentence-level spoken language. Our architecture has two distinctive characteristics. First, it extracts the high-level features from both text and audio via a hybrid deep multimodal structure, which considers the spatial information from text, temporal information from audio, and high-level associations from low-level handcrafted features. Second, we fuse all features by using a three-layer deep neural network to learn the correlations across modalities and train the feature extraction and fusion mo…
While various end-to-end models for spoken language understanding tasks have been explored recently, this paper is probably the first known attempt to challenge the very difficult task of end-to-end spoken question answering (SQA). Learning from the very successful BERT model for various text processing tasks, here we proposed an audio-and-text jointly learned SpeechBERT model. This model outperformed the conventional approach of cascading ASR with the following text question answering (TQA) model on datasets including ASR errors in answer spans, because the end-to-end model was shown to be ab…
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. T…
In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to. We demonstrate that these audio-visual associative localizations emerge from network-internal representations learned as a by-product of training to perform an image-audio retrieval task. Our models operate directly on the image pixels and speech waveform, and do not rely on any conventional supervision in the form of labels, segmentations, or alignments between the modalities during training. We perform analysis…
MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Language
National University of Science and Technology POLITEHNICA Bucharest（波兰亚技术大学布加勒斯特分校）；Paris 1 Panthéon-Sorbonne University（巴黎第一大学）；University of Bucharest（布加勒斯特大学）
Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural language understanding module that transforms the resulting text (or top N hypotheses) into a set of domains, intents, and arguments. These modules are typically optimized independently. In this paper, we formulate audio to semantic understanding as a sequence-to-sequence problem [1]. We propose and compare various encoder-decoder based approaches that optimize both modules jointly, in an end-to-end manner. Evaluations on a…
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）
Given a collection of images and spoken audio captions, we present a method for discovering word-like acoustic units in the continuous speech signal and grounding them to semantically relevant image regions. For example, our model is able to detect spoken instances of the word 'lighthouse' within an utterance and associate them with image regions containing lighthouses. We do not use any form of conventional automatic speech recognition, nor do we use any text transcriptions or conventional linguistic annotations. Our model effectively implements a form of spoken language acquisition, in which…
Abusive content detection in spoken text can be addressed by performing Automatic Speech Recognition (ASR) and leveraging advancements in natural language processing. However, ASR models introduce latency and often perform sub-optimally for profane words as they are underrepresented in training corpora and not spoken clearly or completely. Exploration of this problem entirely in the audio domain has largely been limited by the lack of audio datasets. Building on these challenges, we propose ADIMA, a novel, linguistically diverse, ethically sourced, expert annotated and well-balanced multilingu…
Generative Spoken Language Model based on continuous word-sized audio tokens
ENS（巴黎高等师范学院）；INRIA（法国国家信息与自动化研究所）；INSERM（法国国家健康与医学研究院）；UPEC（巴黎第十二大学）；PSL Research University（巴黎文理研究大学）；Meta AI；The Hebrew University of Jerusalem（希伯来大学）
In this paper, we introduce a new task, spoken video grounding (SVG), which aims to localize the desired video fragments from spoken language descriptions. Compared with using text, employing audio requires the model to directly exploit the useful phonemes and syllables related to the video from raw speech. Moreover, we randomly add environmental noises to this speech audio, further increasing the difficulty of this task and better simulating real applications. To rectify the discriminative phonemes and extract video-related information from noisy audio, we develop a novel video-guided curricu…
Retrieving spoken content with spoken queries, or query-by- example spoken term detection (STD), is attractive because it makes possible the matching of signals directly on the acoustic level without transcribing them into text. Here, we propose an end-to-end query-by-example STD model based on an attention-based multi-hop network, whose input is a spoken query and an audio segment containing several utterances; the output states whether the audio segment includes the query. The model can be trained in either a supervised scenario using labeled data, or in an unsupervised fashion. In the super…
Meta AI Research（元人工智能研究院）；EHESS（法国高等社会科学研究院）；Inria（法国国家信息与自动化研究所）
We introduce dGSLM, the first "textless" model able to generate audio samples of naturalistic spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with a dual-tower transformer architecture with cross-attention trained on 2000 hours of two-channel raw conversational audio (Fisher dataset) without any text or labels. We show that our model is able to generate speech, laughter and other paralinguistic signals in the two channels simultaneously and reproduces more naturalistic and fluid turn-taking compared to a text-based cascaded model.
Amazon Alexa AI（亚马逊Alexa人工智能部门）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Voice Assistants such as Alexa, Siri, and Google Assistant typically use a two-stage Spoken Language Understanding pipeline; first, an Automatic Speech Recognition (ASR) component to process customer speech and generate text transcriptions, followed by a Natural Language Understanding (NLU) component to map transcriptions to an actionable hypothesis. An end-to-end (E2E) system that goes directly from speech to a hypothesis is a more attractive option. These systems were shown to be smaller, faster, and better optimized. However, they require massive amounts of end-to-end training data and in a…
University of Toronto（多伦多大学）；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--社会科学高等研究院--法国国家信息与自动化研究所--巴黎文理研究大学））；Facebook AI Research（脸书人工智能研究院）
We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels. The challenge is based on the Libri-light dataset, which provides up to 60k hours of audio from English audio books without any associated text. We provide a pipeline baseline system consisting on an encoder based on contrastive predictive coding (CPC), a quantizer ($k$-means) and a standard language model (BERT or LSTM). The metrics evaluate the learned representations at the acoustic (ABX discrimination), lexical (spot-the-word), syntactic (ac…
Recent work in spoken language modeling shows the possibility of learning a language unsupervisedly from raw audio without any text labels. The approach relies first on transforming the audio into a sequence of discrete units (or pseudo-text) and then training a language model directly on such pseudo-text. Is such a discrete bottleneck necessary, potentially introducing irreversible errors in the encoding of the speech signal, or could we learn a language model without discrete units at all? In this work, we study the role of discrete versus continuous representations in spoken language modeli…
When people observe events, they are able to abstract key information and build concise summaries of what is happening. These summaries include contextual and semantic information describing the important high-level details (what, where, who and how) of the observed event and exclude background information that is deemed unimportant to the observer. With this in mind, the descriptions people generate for videos of different dynamic events can greatly improve our understanding of the key information of interest in each video. These descriptions can be captured in captions that provide expanded …
Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained on that data. We introduce Spoken ObjectNet, which is designed to remove some of these biases and provide a way to better evaluate how effectively models will perform in real-world scenarios. This dataset expands upon ObjectNet, which is a bias-controlled image dataset that features similar image classes to those present in ImageNet. We detail our data collec…
Spoken language understanding (SLU) refers to the process of inferring the semantic information from audio signals. While the neural transformers consistently deliver the best performance among the state-of-the-art neural architectures in field of natural language processing (NLP), their merits in a closely related field, i.e., spoken language understanding (SLU) have not beed investigated. In this paper, we introduce an end-to-end neural transformer-based SLU model that can predict the variable-length domain, intent, and slots vectors embedded in an audio signal with no intermediate token pre…
We present the corpus called HealthCall. This was recorded in real-life conditions in the call center of Malakoff Humanis. It includes two separate audio channels, the first one for the customer and the second one for the agent. Each conversation was anonymized respecting the General Data Protection Regulation. This corpus includes a transcription of the spoken conversations and was divided into two sets: Train and Devel sets. Two important customer relationship management tasks were assessed on the HealthCall corpus: Automatic prediction of type of user requests and complaints detection. For …
End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. It promises to improve the performance of assistant systems by leveraging acoustic information lost in the intermediate textual representation and preventing cascading errors from Automatic Speech Recognition (ASR). Further, having one unified model has efficiency advantages when deploying assistant systems on-device. However, the limited number of public audio datasets with semantic parse labels hinders the research progress in this area. In this paper, we release the Spoken Task-Oriented …
We propose a novel deliberation-based approach to end-to-end (E2E) spoken language understanding (SLU), where a streaming automatic speech recognition (ASR) model produces the first-pass hypothesis and a second-pass natural language understanding (NLU) component generates the semantic parse by conditioning on both ASR's text and audio embeddings. By formulating E2E SLU as a generalized decoder, our system is able to support complex compositional semantic structures. Furthermore, the sharing of parameters between ASR and NLU makes the system especially suitable for resource-constrained (on-devi…
End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a challenge, largely due to the scarcity of paired audio-semantics data. In this paper, we treat an E2E system as a multi-modal model, with audio and text functioning as its two modalities, and use a cross-modal latent space (CMLS) architecture, where a shared latent space is learned between the `acoustic' and `text' embeddings. We propose using different multi-modal losses to explicitly guide the acoustic embeddings t…
Introduction: Alzheimer's disease is a type of dementia in which early diagnosis plays a major rule in the quality of treatment. Among new works in the diagnosis of Alzheimer's disease, there are many of them analyzing the voice stream acoustically, syntactically or both. The mostly used tools to perform these analysis usually include machine learning techniques. Objective: Designing an automatic machine learning based diagnosis system will help in the procedure of early detection. Also, systems, using noninvasive data are preferable. Methods: We used are classification system based on spoken …
In this work, we define barge-in verification as a supervised learning task where audio-only information is used to classify user spoken dialogue into true and false barge-ins. Following the success of pre-trained models, we use low-level speech representations from a self-supervised representation learning model for our downstream classification task. Further, we propose a novel technique to infuse lexical information directly into speech representations to improve the domain-specific language information implicitly learned during pre-training. Experiments conducted on spoken dialog data show…
Imperial College London（帝国理工学院）；Samsung AI Centre, Cambridge（三星人工智能中心（剑桥））；Facebook London（Facebook（伦敦））
The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and acoustic scene classification. However, self-supervision remains under-explored for audiovisual speech. We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from au…
