Syllables are compositional units of spoken language that play a crucial role in human speech perception and production. However, current neural speech representations lack structure, resulting in dense token sequences that are costly to process. To bridge this gap, we propose a new model, Sylber, that produces speech representations with clean and robust syllabic structure. Specifically, we propose a self-supervised model that regresses features on syllabic segments distilled from a teacher model which is an exponential moving average of the model in training. This results in a highly structured representation of speech features, offering three key benefits: 1) a fast, linear-time syllable segmentation algorithm, 2) efficient syllabic tokenization with an average of 4.27 tokens per second, and 3) syllabic units better suited for lexical and syntactic understanding. We also train token-to-speech generative models with our syllabic units and show that fully intelligible speech can be reconstructed from these tokens. Lastly, we observe that categorical perception, a linguistic phenomenon of speech perception, emerges naturally in our model, making the embedding space more categorical and sparse than previous self-supervised learning approaches. Together, we present a novel self-supervised approach for representing speech as syllables, with significant potential for efficient speech tokenization and spoken language modeling.

Data-driven unit discovery in self-supervised learning (SSL) of speech has embarked on a new era of spoken language processing. Yet, the discovered units often remain in phonetic space and the units beyond phonemes are largely underexplored. Here, we demonstrate that a syllabic organization emerges in learning sentence-level representation of speech. In particular, we adopt "self-distillation" objective to fine-tune the pretrained HuBERT with an aggregator token that summarizes the entire sentence. Without any supervision, the resulting model draws definite boundaries in speech, and the representations across frames exhibit salient syllabic structures. We demonstrate that this emergent structure largely corresponds to the ground truth syllables. Furthermore, we propose a new benchmark task, Spoken Speech ABX, for evaluating sentence-level representation of speech. When compared to previous models, our model outperforms in both unsupervised syllable discovery and learning sentence-level representation. Together, we demonstrate that the self-distillation of HuBERT gives rise to syllabic organization without relying on external labels or modalities, and potentially provides novel data-driven units for spoken language modeling.

Self-Supervised Learning (SSL) based models of speech have shown remarkable performance on a range of downstream tasks. These state-of-the-art models have remained blackboxes, but many recent studies have begun "probing" models like HuBERT, to correlate their internal representations to different aspects of speech. In this paper, we show "inference of articulatory kinematics" as fundamental property of SSL models, i.e., the ability of these models to transform acoustics into the causal articulatory dynamics underlying the speech signal. We also show that this abstraction is largely overlapping across the language of the data used to train the model, with preference to the language with similar phonological system. Furthermore, we show that with simple affine transformations, Acoustic-to-Articulatory inversion (AAI) is transferrable across speakers, even across genders, languages, and dialects, showing the generalizability of this property. Together, these results shed new light on the internals of SSL models that are critical to their superior performance, and open up new avenues into language-agnostic universal models for speech engineering, that are interpretable and grounded in speech science.

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.

With recent advancements in language technologies, humansare now interacting with technology through speech. To in-crease the reach of these technologies, we need to build suchsystems in local languages. A major bottleneck here are theunderlying data-intensive parts that make up such systems,including automatic speech recognition (ASR) systems thatrequire large amounts of labelled data. With the aim of aidingdevelopment of dialog systems in low resourced languages,we propose a novel acoustics based intent recognition systemthat uses discovered phonetic units for intent classification.The system is made up of two blocks - the first block gen-erates a transcript of discovered phonetic units for the inputaudio, and the second block which performs intent classifi-cation from the generated phonemic transcripts. Our workpresents results for such a system for two languages families- Indic languages and Romance languages, for two differentintent recognition tasks. We also perform multilingual train-ing of our intent classifier and show improved cross-lingualtransfer and performance on an unknown language with zeroresources in the same language family.

This paper extends recent work on nonlinear Independent Component Analysis (ICA) by introducing a theoretical framework for nonlinear Independent Subspace Analysis (ISA) in the presence of auxiliary variables. Observed high dimensional acoustic features like log Mel spectrograms can be considered as surface level manifestations of nonlinear transformations over individual multivariate sources of information like speaker characteristics, phonological content etc. Under assumptions of energy based models we use the theory of nonlinear ISA to propose an algorithm that learns unsupervised speech representations whose subspaces are independent and potentially highly correlated with the original non-stationary multivariate sources. We show how nonlinear ICA with auxiliary variables can be extended to a generic identifiable model for subspaces as well while also providing sufficient conditions for the identifiability of these high dimensional subspaces. Our proposed methodology is generic and can be integrated with standard unsupervised approaches to learn speech representations with subspaces that can theoretically capture independent higher order speech signals. We evaluate the gains of our algorithm when integrated with the Autoregressive Predictive Decoding (APC) model by showing empirical results on the speaker verification and phoneme recognition tasks.

We are enveloped by stories of visual interpretations in our everyday lives. The way we narrate a story often comprises of two stages, which are, forming a central mind map of entities and then weaving a story around them. A contributing factor to coherence is not just basing the story on these entities but also, referring to them using appropriate terms to avoid repetition. In this paper, we address these two stages of introducing the right entities at seemingly reasonable junctures and also referring them coherently in the context of visual storytelling. The building blocks of the central mind map, also known as entity skeleton are entity chains including nominal and coreference expressions. This entity skeleton is also represented in different levels of abstractions to compose a generalized frame to weave the story. We build upon an encoder-decoder framework to penalize the model when the decoded story does not adhere to this entity skeleton. We establish a strong baseline for skeleton informed generation and then extend this to have the capability of multitasking by predicting the skeleton in addition to generating the story. Finally, we build upon this model and propose a glocal hierarchical attention model that attends to the skeleton both at the sentence (local) and the story (global) levels. We observe that our proposed models outperform the baseline in terms of automatic evaluation metric, METEOR. We perform various analysis targeted to evaluate the performance of our task of enforcing the entity skeleton such as the number and diversity of the entities generated. We also conduct human evaluation from which it is concluded that the visual stories generated by our model are preferred 82% of the times. In addition, we show that our glocal hierarchical attention model improves coherence by introducing more pronouns as required by the presence of nouns.

Generating a long, coherent text such as a paragraph requires a high-level control of different levels of relations between sentences (e.g., tense, coreference). We call such a logical connection between sentences as a (paragraph) flow. In order to produce a coherent flow of text, we explore two forms of intersentential relations in a paragraph: one is a human-created linguistical relation that forms a structure (e.g., discourse tree) and the other is a relation from latent representation learned from the sentences themselves. Our two proposed models incorporate each form of relations into document-level language models: the former is a supervised model that jointly learns a language model as well as discourse relation prediction, and the latter is an unsupervised model that is hierarchically conditioned by a recurrent neural network (RNN) over the latent information. Our proposed models with both forms of relations outperform the baselines in partially conditioned paragraph generation task. Our codes and data are publicly available.

We study the problem of generating interesting endings for stories. Neural generative models have shown promising results for various text generation problems. Sequence to Sequence (Seq2Seq) models are typically trained to generate a single output sequence for a given input sequence. However, in the context of a story, multiple endings are possible. Seq2Seq models tend to ignore the context and generate generic and dull responses. Very few works have studied generating diverse and interesting story endings for a given story context. In this paper, we propose models which generate more diverse and interesting outputs by 1) training models to focus attention on important keyphrases of the story, and 2) promoting generation of non-generic words. We show that the combination of the two leads to more diverse and interesting endings.

Those discussions have focused on data collection, experimental design, and interventions in modeling. But we argue that we ought to first understand the frameworks of ethics that are being used to evaluate the fairness and justice of algorithmic systems. Here, we begin that discussion by outlining deontological ethics, and envision a research agenda prioritized by it. Due to the sheer global reach of machine learning and NLP applications, they are empowered to impact societies (Hovy and Spruit, 2016) - potentially for the worse. Potential harms include exclusion of communities due to demographic bias, overgeneralization of model predictions to amplify bias or prejudice, and overstepping privacy concerns in the pursuit of data and quantification (Mieskes, 2017).