Emmanuel Dupoux

Paden Tomasello, Akshat Shrivastava, Daniel Lazar et al. · meta-ai, uw

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 semantic Parsing (STOP) dataset, the largest and most complex SLU dataset to be publicly available. Additionally, we define low-resource splits to establish a benchmark for improving SLU when limited labeled data is available. Furthermore, in addition to the human-recorded audio, we are releasing a TTS-generated version to benchmark the performance for low-resource domain adaptation of end-to-end SLU systems. Initial experimentation show end-to-end SLU models performing slightly worse than their cascaded counterparts, which we hope encourages future work in this direction.

Tu Anh Nguyen, Wei-Ning Hsu, Antony D'Avirro et al.

Recent work has shown that it is possible to resynthesize high-quality speech based, not on text, but on low bitrate discrete units that have been learned in a self-supervised fashion and can therefore capture expressive aspects of speech that are hard to transcribe (prosody, voice styles, non-verbal vocalization). The adoption of these methods is still limited by the fact that most speech synthesis datasets are read, severely limiting spontaneity and expressivity. Here, we introduce Expresso, a high-quality expressive speech dataset for textless speech synthesis that includes both read speech and improvised dialogues rendered in 26 spontaneous expressive styles. We illustrate the challenges and potentials of this dataset with an expressive resynthesis benchmark where the task is to encode the input in low-bitrate units and resynthesize it in a target voice while preserving content and style. We evaluate resynthesis quality with automatic metrics for different self-supervised discrete encoders, and explore tradeoffs between quality, bitrate and invariance to speaker and style. All the dataset, evaluation metrics and baseline models are open source

Maureen de Seyssel, Guillaume Wisniewski, Emmanuel Dupoux · apple-ml

According to the Language Familiarity Effect (LFE), people are better at discriminating between speakers of their native language. Although this cognitive effect was largely studied in the literature, experiments have only been conducted on a limited number of language pairs and their results only show the presence of the effect without yielding a gradual measure that may vary across language pairs. In this work, we show that the computational model of LFE introduced by Thorburn, Feldmand and Schatz (2019) can address these two limitations. In a first experiment, we attest to this model's capacity to obtain a gradual measure of the LFE by replicating behavioural findings on native and accented speech. In a second experiment, we evaluate LFE on a large number of language pairs, including many which have never been tested on humans. We show that the effect is replicated across a wide array of languages, providing further evidence of its universality. Building on the gradual measure of LFE, we also show that languages belonging to the same family yield smaller scores, supporting the idea of an effect of language distance on LFE.

Mathieu Rita, Corentin Tallec, Paul Michel et al.

Lewis signaling games are a class of simple communication games for simulating the emergence of language. In these games, two agents must agree on a communication protocol in order to solve a cooperative task. Previous work has shown that agents trained to play this game with reinforcement learning tend to develop languages that display undesirable properties from a linguistic point of view (lack of generalization, lack of compositionality, etc). In this paper, we aim to provide better understanding of this phenomenon by analytically studying the learning problem in Lewis games. As a core contribution, we demonstrate that the standard objective in Lewis games can be decomposed in two components: a co-adaptation loss and an information loss. This decomposition enables us to surface two potential sources of overfitting, which we show may undermine the emergence of a structured communication protocol. In particular, when we control for overfitting on the co-adaptation loss, we recover desired properties in the emergent languages: they are more compositional and generalize better.

Maxime Poli, Mahi Luthra, Youssef Benchekroun et al.

The parallel advances in language modeling and speech representation learning have raised the prospect of learning language directly from speech without textual intermediates. This requires extracting semantic representations directly from speech. Our contributions are threefold. First, we introduce SpidR, a self-supervised speech representation model that efficiently learns representations with highly accessible phonetic information, which makes it particularly suited for textless spoken language modeling. It is trained on raw waveforms using a masked prediction objective combined with self-distillation and online clustering. The intermediate layers of the student model learn to predict assignments derived from the teacher's intermediate layers. This learning objective stabilizes the online clustering procedure compared to previous approaches, resulting in higher quality codebooks. SpidR outperforms wav2vec 2.0, HuBERT, WavLM, and DinoSR on downstream language modeling benchmarks (sWUGGY, sBLIMP, tSC). Second, we systematically evaluate across models and layers the correlation between speech unit quality (ABX, PNMI) and language modeling performance, validating these metrics as reliable proxies. Finally, SpidR significantly reduces pretraining time compared to HuBERT, requiring only one day of pretraining on 16 GPUs, instead of a week. This speedup is enabled by the pretraining method and an efficient codebase, which allows faster iteration and easier experimentation. We open-source the training code and model checkpoints at https://github.com/facebookresearch/spidr.

Robin Algayres, Yossi Adi, Tu Anh Nguyen et al.

In NLP, text language models based on words or subwords are known to outperform their character-based counterparts. Yet, in the speech community, the standard input of spoken LMs are 20ms or 40ms-long discrete units (shorter than a phoneme). Taking inspiration from word-based LM, we introduce a Generative Spoken Language Model (GSLM) based on word-size continuous-valued audio embeddings that can generate diverse and expressive language output. This is obtained by replacing lookup table for lexical types with a Lexical Embedding function, the cross entropy loss by a contrastive loss, and multinomial sampling by k-NN sampling. The resulting model is the first generative language model based on word-size continuous embeddings. Its performance is on par with discrete unit GSLMs regarding generation quality as measured by automatic metrics and subjective human judgements. Moreover, it is five times more memory efficient thanks to its large 200ms units. In addition, the embeddings before and after the Lexical Embedder are phonetically and semantically interpretable.

Maureen de Seyssel, Marvin Lavechin, Hadrien Titeux et al. · apple-ml

We present ProsAudit, a benchmark in English to assess structural prosodic knowledge in self-supervised learning (SSL) speech models. It consists of two subtasks, their corresponding metrics, and an evaluation dataset. In the protosyntax task, the model must correctly identify strong versus weak prosodic boundaries. In the lexical task, the model needs to correctly distinguish between pauses inserted between words and within words. We also provide human evaluation scores on this benchmark. We evaluated a series of SSL models and found that they were all able to perform above chance on both tasks, even when evaluated on an unseen language. However, non-native models performed significantly worse than native ones on the lexical task, highlighting the importance of lexical knowledge in this task. We also found a clear effect of size with models trained on more data performing better in the two subtasks.

Itai Gat, Felix Kreuk, Tu Anh Nguyen et al.

Generative Spoken Language Modeling research focuses on optimizing speech Language Models (LMs) using raw audio recordings without accessing any textual supervision. Such speech LMs usually operate over discrete units obtained from quantizing internal representations of self-supervised models. Although such units show impressive modeling results, their robustness capabilities have not been extensively investigated. This work focuses on improving the robustness of discrete input representations for generative spoken language modeling. First, we formally define how to measure the robustness of such representations to various signal variations that do not alter the spoken information (e.g., time-stretch). Next, we empirically demonstrate how current state-of-the-art representation models lack robustness to such variations. To overcome this, we propose an effective and efficient method to learn robust discrete speech representation for generative spoken language modeling. The proposed approach is based on applying a set of signal transformations to the speech signal and optimizing the model using an iterative pseudo-labeling scheme. Our method significantly improves over the evaluated baselines when considering encoding and modeling metrics. We additionally evaluate our method on the speech-to-speech translation task, considering Spanish-English and French-English translations, and show the proposed approach outperforms the evaluated baselines.

Tu Anh Nguyen, Benoit Sagot, Emmanuel Dupoux

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 modeling. We show that discretization is indeed essential for good results in spoken language modeling. We show that discretization removes linguistically irrelevant information from the continuous features, helping to improve language modeling performances. On the basis of this study, we train a language model on the discrete units of the HuBERT features, reaching new state-of-the-art results in the lexical, syntactic and semantic metrics of the Zero Resource Speech Challenge 2021 (Track 1 - Speech Only).

Tu Anh Nguyen, Maureen de Seyssel, Robin Algayres et al. · apple-ml

Word or word-fragment based Language Models (LM) are typically preferred over character-based ones in many downstream applications. This may not be surprising as words seem more linguistically relevant units than characters. Words provide at least two kinds of relevant information: boundary information and meaningful units. However, word boundary information may be absent or unreliable in the case of speech input (word boundaries are not marked explicitly in the speech stream). Here, we systematically compare LSTMs as a function of the input unit (character, phoneme, word, word part), with or without gold boundary information. We probe linguistic knowledge in the networks at the lexical, syntactic and semantic levels using three speech-adapted black box NLP psycholinguistically-inpired benchmarks (pWUGGY, pBLIMP, pSIMI). We find that the absence of boundaries costs between 2\% and 28\% in relative performance depending on the task. We show that gold boundaries can be replaced by automatically found ones obtained with an unsupervised segmentation algorithm, and that even modest segmentation performance gives a gain in performance on two of the three tasks compared to basic character/phone based models without boundary information.

Robin Algayres, Tristan Ricoul, Julien Karadayi et al.

Finding word boundaries in continuous speech is challenging as there is little or no equivalent of a 'space' delimiter between words. Popular Bayesian non-parametric models for text segmentation use a Dirichlet process to jointly segment sentences and build a lexicon of word types. We introduce DP-Parse, which uses similar principles but only relies on an instance lexicon of word tokens, avoiding the clustering errors that arise with a lexicon of word types. On the Zero Resource Speech Benchmark 2017, our model sets a new speech segmentation state-of-the-art in 5 languages. The algorithm monotonically improves with better input representations, achieving yet higher scores when fed with weakly supervised inputs. Despite lacking a type lexicon, DP-Parse can be pipelined to a language model and learn semantic and syntactic representations as assessed by a new spoken word embedding benchmark.

Mahi Luthra, Jiayi Shen, Maxime Poli et al.

Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compared to the data-hungry self-supervised speech models. To address this gap, this paper introduces SpidR-Adapt for rapid adaptation to new languages using minimal unlabeled data. We cast such low-resource speech representation learning as a meta-learning problem and construct a multi-task adaptive pre-training (MAdaPT) protocol which formulates the adaptation process as a bi-level optimization framework. To enable scalable meta-training under this framework, we propose a novel heuristic solution, first-order bi-level optimization (FOBLO), avoiding heavy computation costs. Finally, we stabilize meta-training by using a robust initialization through interleaved supervision which alternates self-supervised and supervised objectives. Empirically, SpidR-Adapt achieves rapid gains in phonemic discriminability (ABX) and spoken language modeling (sWUGGY, sBLIMP, tSC), improving over in-domain language models after training on less than 1h of target-language audio, over $100\times$ more data-efficient than standard training. These findings highlight a practical, architecture-agnostic path toward biologically inspired, data-efficient representations. We open-source the training code and model checkpoints at https://github.com/facebookresearch/spidr-adapt.

Marvin Lavechin, Yaya Sy, Hadrien Titeux et al.

Self-supervised techniques for learning speech representations have been shown to develop linguistic competence from exposure to speech without the need for human labels. In order to fully realize the potential of these approaches and further our understanding of how infants learn language, simulations must closely emulate real-life situations by training on developmentally plausible corpora and benchmarking against appropriate test sets. To this end, we propose a language-acquisition-friendly benchmark to probe spoken language models at the lexical and syntactic levels, both of which are compatible with the vocabulary typical of children's language experiences. This paper introduces the benchmark and summarizes a range of experiments showing its usefulness. In addition, we highlight two exciting challenges that need to be addressed for further progress: bridging the gap between text and speech and between clean speech and in-the-wild speech.

Maxime Poli, Emmanuel Dupoux, Rachid Riad

Parts of the brain that carry sensory tasks are organized topographically: nearby neurons are responsive to the same properties of input signals. Thus, in this work, inspired by the neuroscience literature, we proposed a new topographic inductive bias in Convolutional Neural Networks (CNNs). To achieve this, we introduced a new topographic loss and an efficient implementation to topographically organize each convolutional layer of any CNN. We benchmarked our new method on 4 datasets and 3 models in vision and audio tasks and showed equivalent performance to all benchmarks. Besides, we also showcased the generalizability of our topographic loss with how it can be used with different topographic organizations in CNNs. Finally, we demonstrated that adding the topographic inductive bias made CNNs more resistant to pruning. Our approach provides a new avenue to obtain models that are more memory efficient while maintaining better accuracy.

Robin Algayres, Adel Nabli, Benoit Sagot et al.

We introduce a simple neural encoder architecture that can be trained using an unsupervised contrastive learning objective which gets its positive samples from data-augmented k-Nearest Neighbors search. We show that when built on top of recent self-supervised audio representations, this method can be applied iteratively and yield competitive SSE as evaluated on two tasks: query-by-example of random sequences of speech, and spoken term discovery. On both tasks our method pushes the state-of-the-art by a significant margin across 5 different languages. Finally, we establish a benchmark on a query-by-example task on the LibriSpeech dataset to monitor future improvements in the field.

Ewan Dunbar, Nicolas Hamilakis, Emmanuel Dupoux

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 cumulative progress. We present an overview of the six editions of this challenge series since 2015, discuss the lessons learned, and outline the areas which need more work or give puzzling results.

Youssef Benchekroun, Megi Dervishi, Mark Ibrahim et al.

We propose WorldSense, a benchmark designed to assess the extent to which LLMs are consistently able to sustain tacit world models, by testing how they draw simple inferences from descriptions of simple arrangements of entities. Worldsense is a synthetic benchmark with three problem types, each with their own trivial control, which explicitly avoids bias by decorrelating the abstract structure of problems from the vocabulary and expressions, and by decorrelating all problem subparts with the correct response. We run our benchmark on three state-of-the-art chat-LLMs (GPT3.5, GPT4 and Llama2-chat) and show that these models make errors even with as few as three objects. Furthermore, they have quite heavy response biases, preferring certain responses irrespective of the question. Errors persist even with chain-of-thought prompting and in-context learning. Lastly, we show that while finetuning on similar problems does result in substantial improvements -- within- and out-of-distribution -- the finetuned models do not generalise beyond a constraint problem space.

Mark Hallap, Emmanuel Dupoux, Ewan Dunbar

Unsupervised speech representations have taken off, with benchmarks (SUPERB, ZeroSpeech) demonstrating major progress on semi-supervised speech recognition, speech synthesis, and speech-only language modelling. Inspiration comes from the promise of ``discovering the phonemes'' of a language or a similar low-bitrate encoding. However, one of the critical properties of phoneme transcriptions is context-invariance: the phonetic context of a speech sound can have massive influence on the way it is pronounced, while the text remains stable. This is what allows tokens of the same word to have the same transcriptions -- key to language understanding. Current benchmarks do not measure context-invariance. We develop a new version of the ZeroSpeech ABX benchmark that measures context-invariance, and apply it to recent self-supervised representations. We demonstrate that the context-independence of representations is predictive of the stability of word-level representations. We suggest research concentrate on improving context-independence of self-supervised and unsupervised representations.

Maxime Poli, Emmanuel Chemla, Emmanuel Dupoux

Recent progress in Spoken Language Modeling has shown that learning language directly from speech is feasible. Generating speech through a pipeline that operates at the text level typically loses nuances, intonations, and non-verbal vocalizations. Modeling directly from speech opens up the path to more natural and expressive systems. On the other hand, speech-only systems require up to three orders of magnitude more data to catch up to their text-based counterparts in terms of their semantic abilities. We show that fine-tuning speech representation models on phoneme classification leads to more context-invariant representations, and language models trained on these units achieve comparable lexical comprehension to ones trained on hundred times more data.

Robin Algayres, Pablo Diego-Simon, Benoit Sagot et al.

Due to the absence of explicit word boundaries in the speech stream, the task of segmenting spoken sentences into word units without text supervision is particularly challenging. In this work, we leverage the most recent self-supervised speech models that have proved to quickly adapt to new tasks through fine-tuning, even in low resource conditions. Taking inspiration from semi-supervised learning, we fine-tune an XLS-R model to predict word boundaries themselves produced by top-tier speech segmentation systems: DPDP, VG-HuBERT, GradSeg and DP-Parse. Once XLS-R is fine-tuned, it is used to infer new word boundary labels that are used in turn for another fine-tuning step. Our method consistently improves the performance of each system and sets a new state-of-the-art that is, on average 130% higher than the previous one as measured by the F1 score on correctly discovered word tokens on five corpora featuring different languages. Finally, our system can segment speech from languages unseen during fine-tuning in a zero-shot fashion.

Emmanuel Dupoux, Yann LeCun, Jitendra Malik

We critically examine the limitations of current AI models in achieving autonomous learning and propose a learning architecture inspired by human and animal cognition. The proposed framework integrates learning from observation (System A) and learning from active behavior (System B) while flexibly switching between these learning modes as a function of internally generated meta-control signals (System M). We discuss how this could be built by taking inspiration on how organisms adapt to real-world, dynamic environments across evolutionary and developmental timescales.

Maxime Poli, Manel Khentout, Angelo Ortiz Tandazo et al.

We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev and 6 test languages, chosen to span a wide range of phonemic contrasts. Given only 10 hours of speech in a previously unseen language, systems must produce discrete units that are mapped to a predefined phoneme inventory, through either a many-to-one or a one-to-one assignment. The resulting sequences are evaluated for unit quality, recognition and segmentation. We provide four pretrained multilingual HuBERT and SpidR baselines, and show that phonemic information is available enough in current models for derived units to correlate well with phonemes, though with variations across languages.

Dongyan Lin, Phillip Rust, Angel Villar Corrales et al.

Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal models. Recent research suggests current vision-language models (VLMs) trained on curated web data fail to generalize to the sparse, weakly-aligned egocentric streams produced by wearable devices, embodied agents, and infant head-cams -- and no fixed evaluation pipeline exists for measuring progress on this regime. We train VLMs on datasets with varying degrees of semantic alignment between visual and linguistic inputs, including naturalistic infant and adult egocentric videos, and evaluate them with a comprehensive suite spanning multimodal language grounding and unimodal vision and language tasks. At the core of this suite is Machine-DevBench, a corpus-grounded benchmark of lexical and grammatical competence, automatically generated from the model's training vocabulary across logarithmic frequency bins to eliminate the train/eval mismatch and low statistical power of prior developmental benchmarks. Our results show that current VLM paradigms hinge on the tight semantic alignment of curated data and fail to exploit the weakly-aligned signal that dominates naturalistic egocentric input -- the very regime in which humans thrive. To motivate progress, we introduce the EgoBabyVLM Challenge to drive the development of models capable of grounded language learning from the kind of naturalistic data that human infants experience.

Maxime Poli, Emmanuel Chemla, Emmanuel Dupoux

We introduce fastabx, a high-performance Python library for building ABX discrimination tasks. ABX is a measure of the separation between generic categories of interest. It has been used extensively to evaluate phonetic discriminability in self-supervised speech representations. However, its broader adoption has been limited by the absence of adequate tools. fastabx addresses this gap by providing a framework capable of constructing any type of ABX task while delivering the efficiency necessary for rapid development cycles, both in task creation and in calculating distances between representations. We believe that fastabx will serve as a valuable resource for the broader representation learning community, enabling researchers to systematically investigate what information can be directly extracted from learned representations across several domains beyond speech processing. The source code is available at https://github.com/bootphon/fastabx.

Angelo Ortiz Tandazo, Manel Khentout, Youssef Benchekroun et al.

This paper introduces MauBERT, a multilingual extension of HuBERT that leverages articulatory features for robust cross-lingual phonetic representation learning. We continue HuBERT pre-training with supervision based on a phonetic-to-articulatory feature mapping in 55 languages. Our models learn from multilingual data to predict articulatory features or phones, resulting in language-independent representations that capture multilingual phonetic properties. Through comprehensive ABX discriminability testing, we show MauBERT models produce more context-invariant representations than state-of-the-art multilingual self-supervised learning models. Additionally, the models effectively adapt to unseen languages and casual speech with minimal self-supervised fine-tuning (10 hours of speech). This establishes an effective approach for instilling linguistic inductive biases in self-supervised speech models.

Eugene Kharitonov, Jade Copet, Kushal Lakhotia et al.

Textless spoken language processing research aims to extend the applicability of standard NLP toolset onto spoken language and languages with few or no textual resources. In this paper, we introduce textless-lib, a PyTorch-based library aimed to facilitate research in this research area. We describe the building blocks that the library provides and demonstrate its usability by discuss three different use-case examples: (i) speaker probing, (ii) speech resynthesis and compression, and (iii) speech continuation. We believe that textless-lib substantially simplifies research the textless setting and will be handful not only for speech researchers but also for the NLP community at large. The code, documentation, and pre-trained models are available at https://github.com/facebookresearch/textlesslib/ .

Mathieu Bernard, Maxime Poli, Julien Karadayi et al.

We introduce Shennong, a Python toolbox and command-line utility for speech features extraction. It implements a wide range of well-established state of art algorithms including spectro-temporal filters such as Mel-Frequency Cepstral Filterbanks or Predictive Linear Filters, pre-trained neural networks, pitch estimators as well as speaker normalization methods and post-processing algorithms. Shennong is an open source, easy-to-use, reliable and extensible framework. The use of Python makes the integration to others speech modeling and machine learning tools easy. It aims to replace or complement several heterogeneous software, such as Kaldi or Praat. After describing the Shennong software architecture, its core components and implemented algorithms, this paper illustrates its use on three applications: a comparison of speech features performances on a phones discrimination task, an analysis of a Vocal Tract Length Normalization model as a function of the speech duration used for training and a comparison of pitch estimation algorithms under various noise conditions.

Eugene Kharitonov, Ann Lee, Adam Polyak et al.

Speech pre-training has primarily demonstrated efficacy on classification tasks, while its capability of generating novel speech, similar to how GPT-2 can generate coherent paragraphs, has barely been explored. Generative Spoken Language Modeling (GSLM) \cite{Lakhotia2021} is the only prior work addressing the generative aspects of speech pre-training, which replaces text with discovered phone-like units for language modeling and shows the ability to generate meaningful novel sentences. Unfortunately, despite eliminating the need of text, the units used in GSLM discard most of the prosodic information. Hence, GSLM fails to leverage prosody for better comprehension, and does not generate expressive speech. In this work, we present a prosody-aware generative spoken language model (pGSLM). It is composed of a multi-stream transformer language model (MS-TLM) of speech, represented as discovered unit and prosodic feature streams, and an adapted HiFi-GAN model converting MS-TLM outputs to waveforms. We devise a series of metrics for prosody modeling and generation, and re-use metrics from GSLM for content modeling. Experimental results show that the pGSLM can utilize prosody to improve both prosody and content modeling, and also generate natural, meaningful, and coherent speech given a spoken prompt. Audio samples can be found at https://speechbot.github.io/pgslm. Codes and models are available at https://github.com/pytorch/fairseq/tree/main/examples/textless_nlp/pgslm.

Changhan Wang, Morgane Rivière, Ann Lee et al.

We introduce VoxPopuli, a large-scale multilingual corpus providing 100K hours of unlabelled speech data in 23 languages. It is the largest open data to date for unsupervised representation learning as well as semi-supervised learning. VoxPopuli also contains 1.8K hours of transcribed speeches in 16 languages and their aligned oral interpretations into 5 other languages totaling 5.1K hours. We provide speech recognition baselines and validate the versatility of VoxPopuli unlabelled data in semi-supervised learning under challenging out-of-domain settings. We will release the corpus at https://github.com/facebookresearch/voxpopuli under an open license.

Hadrien Titeux, Rachid Riad, Xuan-Nga Cao et al.

We introduce Seshat, a new, simple and open-source software to efficiently manage annotations of speech corpora. The Seshat software allows users to easily customise and manage annotations of large audio corpora while ensuring compliance with the formatting and naming conventions of the annotated output files. In addition, it includes procedures for checking the content of annotations following specific rules that can be implemented in personalised parsers. Finally, we propose a double-annotation mode, for which Seshat computes automatically an associated inter-annotator agreement with the $γ$ measure taking into account the categorisation and segmentation discrepancies.

Jacob Kahn, Morgane Rivière, Weiyi Zheng et al.

We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books from the LibriVox project. It contains over 60K hours of audio, which is, to our knowledge, the largest freely-available corpus of speech. The audio has been segmented using voice activity detection and is tagged with SNR, speaker ID and genre descriptions. Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-supervised setting (PER, CER) and (3) the distant supervision setting (WER). Settings (2) and (3) use limited textual resources (10 minutes to 10 hours) aligned with the speech. Setting (3) uses large amounts of unaligned text. They are evaluated on the standard LibriSpeech dev and test sets for comparison with the supervised state-of-the-art.

Tu Anh Nguyen, Benjamin Muller, Bokai Yu et al.

We introduce Spirit LM, a foundation multimodal language model that freely mixes text and speech. Our model is based on a 7B pretrained text language model that we extend to the speech modality by continuously training it on text and speech units. Speech and text sequences are concatenated as a single stream of tokens, and trained with a word-level interleaving method using a small automatically-curated speech-text parallel corpus. Spirit LM comes in two versions: a Base version that uses speech phonetic units (HuBERT) and an Expressive version that models expressivity using pitch and style units in addition to the phonetic units. For both versions, the text is encoded with subword BPE tokens. The resulting model displays both the semantic abilities of text models and the expressive abilities of speech models. Additionally, we demonstrate that Spirit LM can learn new tasks in a few-shot fashion across modalities (i.e. ASR, TTS, Speech Classification). We make available model weights and inference code.

Angelo Ortiz Tandazo, Thomas Schatz, Thomas Hueber et al.

As a first step towards a complete computational model of speech learning involving perception-production loops, we investigate the forward mapping between pseudo-motor commands and articulatory trajectories. Two phonological feature sets, based respectively on generative and articulatory phonology, are used to encode a phonetic target sequence. Different interpolation techniques are compared to generate smooth trajectories in these feature spaces, with a potential optimisation of the target value and timing to capture co-articulation effects. We report the Pearson correlation between a linear projection of the generated trajectories and articulatory data derived from a multi-speaker dataset of electromagnetic articulography (EMA) recordings. A correlation of 0.67 is obtained with an extended feature set based on generative phonology and a linear interpolation technique. We discuss the implications of our results for our understanding of the dynamics of biological motion.

Siddhant Arora, Kai-Wei Chang, Chung-Ming Chien et al. · mit, nvidia

The field of spoken language processing is undergoing a shift from training custom-built, task-specific models toward using and optimizing spoken language models (SLMs) which act as universal speech processing systems. This trend is similar to the progression toward universal language models that has taken place in the field of (text) natural language processing. SLMs include both "pure" language models of speech -- models of the distribution of tokenized speech sequences -- and models that combine speech encoders with text language models, often including both spoken and written input or output. Work in this area is very diverse, with a range of terminology and evaluation settings. This paper aims to contribute an improved understanding of SLMs via a unifying literature survey of recent work in the context of the evolution of the field. Our survey categorizes the work in this area by model architecture, training, and evaluation choices, and describes some key challenges and directions for future work.

Quentin Garrido, Nicolas Ballas, Mahmoud Assran et al.

We investigate the emergence of intuitive physics understanding in general-purpose deep neural network models trained to predict masked regions in natural videos. Leveraging the violation-of-expectation framework, we find that video prediction models trained to predict outcomes in a learned representation space demonstrate an understanding of various intuitive physics properties, such as object permanence and shape consistency. In contrast, video prediction in pixel space and multimodal large language models, which reason through text, achieve performance closer to chance. Our comparisons of these architectures reveal that jointly learning an abstract representation space while predicting missing parts of sensory input, akin to predictive coding, is sufficient to acquire an understanding of intuitive physics, and that even models trained on one week of unique video achieve above chance performance. This challenges the idea that core knowledge -- a set of innate systems to help understand the world -- needs to be hardwired to develop an understanding of intuitive physics.

Maureen de Seyssel, Antony D'Avirro, Adina Williams et al.

We introduce EmphAssess, a prosodic benchmark designed to evaluate the capability of speech-to-speech models to encode and reproduce prosodic emphasis. We apply this to two tasks: speech resynthesis and speech-to-speech translation. In both cases, the benchmark evaluates the ability of the model to encode emphasis in the speech input and accurately reproduce it in the output, potentially across a change of speaker and language. As part of the evaluation pipeline, we introduce EmphaClass, a new model that classifies emphasis at the frame or word level.

Pascale Fung, Yoram Bachrach, Asli Celikyilmaz et al.

This paper describes our research on AI agents embodied in visual, virtual or physical forms, enabling them to interact with both users and their environments. These agents, which include virtual avatars, wearable devices, and robots, are designed to perceive, learn and act within their surroundings, which makes them more similar to how humans learn and interact with the environments as compared to disembodied agents. We propose that the development of world models is central to reasoning and planning of embodied AI agents, allowing these agents to understand and predict their environment, to understand user intentions and social contexts, thereby enhancing their ability to perform complex tasks autonomously. World modeling encompasses the integration of multimodal perception, planning through reasoning for action and control, and memory to create a comprehensive understanding of the physical world. Beyond the physical world, we also propose to learn the mental world model of users to enable better human-agent collaboration.

Mathieu Rita, Florian Strub, Rahma Chaabouni et al.

While Reinforcement Learning (RL) has been proven essential for tuning large language models (LLMs), it can lead to reward over-optimization (ROO). Existing approaches address ROO by adding KL regularization, requiring computationally expensive hyperparameter tuning. Additionally, KL regularization focuses solely on regularizing the language policy, neglecting a potential source of regularization: the reward function itself. Inspired by demonstration-guided RL, we here introduce the Reward Calibration from Demonstration (RCfD), which leverages human demonstrations and a reward model to recalibrate the reward objective. Formally, given a prompt, the RCfD objective minimizes the distance between the demonstrations' and LLM's rewards rather than directly maximizing the reward function. This objective shift avoids incentivizing the LLM to exploit the reward model and promotes more natural and diverse language generation. We show the effectiveness of RCfD on three language tasks, which achieves comparable performance to carefully tuned baselines while mitigating ROO.

Florian Bordes, Quentin Garrido, Justine T Kao et al.

We present IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning models. Building on the original IntPhys benchmark, IntPhys 2 focuses on four core principles related to macroscopic objects: Permanence, Immutability, Spatio-Temporal Continuity, and Solidity. These conditions are inspired by research into intuitive physical understanding emerging during early childhood. IntPhys 2 offers a comprehensive suite of tests, based on the violation of expectation framework, that challenge models to differentiate between possible and impossible events within controlled and diverse virtual environments. Alongside the benchmark, we provide performance evaluations of several state-of-the-art models. Our findings indicate that while these models demonstrate basic visual understanding, they face significant challenges in grasping intuitive physics across the four principles in complex scenes, with most models performing at chance levels (50%), in stark contrast to human performance, which achieves near-perfect accuracy. This underscores the gap between current models and human-like intuitive physics understanding, highlighting the need for advancements in model architectures and training methodologies.

Mathieu Rita, Paul Michel, Rahma Chaabouni et al.

Computational modeling plays an essential role in the study of language emergence. It aims to simulate the conditions and learning processes that could trigger the emergence of a structured language within a simulated controlled environment. Several methods have been used to investigate the origin of our language, including agent-based systems, Bayesian agents, genetic algorithms, and rule-based systems. This chapter explores another class of computational models that have recently revolutionized the field of machine learning: deep learning models. The chapter introduces the basic concepts of deep and reinforcement learning methods and summarizes their helpfulness for simulating language emergence. It also discusses the key findings, limitations, and recent attempts to build realistic simulations. This chapter targets linguists and cognitive scientists seeking an introduction to deep learning as a tool to investigate language evolution.

Loann Peurey, Marvin Lavechin, Tarek Kunze et al.

Audio-recordings collected with a child-worn device are a fundamental tool in child language research. Long-form recordings collected over whole days promise to capture children's input and production with minimal observer bias, and therefore high validity. The sheer volume of resulting data necessitates automated analysis to extract relevant metrics for researchers and clinicians. This paper summarizes collective knowledge on this technique, providing entry points to existing resources. We also highlight various sources of error that threaten the accuracy of automated annotations and the interpretation of resulting metrics. To address this, we propose potential troubleshooting metrics to help users assess data quality. While a fully automated quality control system is not feasible, we outline practical strategies for researchers to improve data collection and contextualize their analyses.

Tarek Kunze, Marianne Métais, Hadrien Titeux et al.

Recordings gathered with child-worn devices promised to revolutionize both fundamental and applied speech sciences by allowing the effortless capture of children's naturalistic speech environment and language production. This promise hinges on speech technologies that can transform the sheer mounds of data thus collected into usable information. This paper demonstrates several obstacles blocking progress by summarizing three years' worth of experiments aimed at improving one fundamental task: Voice Type Classification. Our experiments suggest that improvements in representation features, architecture, and parameter search contribute to only marginal gains in performance. More progress is made by focusing on data relevance and quantity, which highlights the importance of collecting data with appropriate permissions to allow sharing.

Robin Algayres, Charles-Éric Saint-James, Mahi Luthra et al.

Children learn to speak with a low amount of data and can be taught new words on a few-shot basis, making them particularly data-efficient learners. The BabyLM challenge aims at exploring language model (LM) training in the low-data regime but uses metrics that concentrate on the head of the word distribution. Here, we introduce LongTail-Swap (LT-Swap), a benchmark that focuses on the tail of the distribution, i.e., measures the ability of LMs to learn new words with very little exposure, like infants do. LT-Swap is a pretraining corpus-specific test set of acceptable versus unacceptable sentence pairs that isolate semantic and syntactic usage of rare words. Models are evaluated in a zero-shot fashion by computing the average log probabilities over the two members of each pair. We built two such test sets associated with the 10M words and 100M words BabyLM training sets, respectively, and evaluated 16 models from the BabyLM leaderboard. Our results not only highlight the poor performance of language models on rare words but also reveal that performance differences across LM architectures are much more pronounced in the long tail than in the head. This offers new insights into which architectures are better at handling rare word generalization. We've also made the code publicly avail

Théo Charlot, Tarek Kunze, Maxime Poli et al.

Child-centered long-form recordings are essential for studying early language development, but existing speech models trained on clean adult data perform poorly due to acoustic and linguistic differences. We introduce BabyHuBERT, the first self-supervised speech representation model trained on 13,000 hours of multilingual child-centered long-form recordings spanning over 40 languages. We evaluate BabyHuBERT on speaker segmentation, identifying when target children speak versus female adults, male adults, or other children -- a fundamental preprocessing step for analyzing naturalistic language experiences. BabyHuBERT achieves F1-scores from 52.1% to 74.4% across six diverse datasets, consistently outperforming W2V2-LL4300 (trained on English long-forms) and standard HuBERT (trained on clean adult speech). Notable improvements include 13.2 absolute F1 points over HuBERT on Vanuatu and 15.9 points on Solomon Islands corpora, demonstrating effectiveness on underrepresented languages. By sharing code and models, BabyHuBERT serves as a foundation model for child speech research, enabling fine-tuning on diverse downstream tasks.

Cihan Xiao, Ruixing Liang, Xiangyu Zhang et al.

The success of large language models has driven interest in developing similar speech processing capabilities. However, a key challenge is the scarcity of high-quality spontaneous speech data, as most existing datasets contain scripted dialogues. To address this, we present a novel pipeline for eliciting and recording natural dialogues and release our dataset with 100+ hours of spontaneous speech. Our approach fosters fluid, natural conversations while encouraging a diverse range of topics and interactive exchanges. Unlike traditional methods, it facilitates genuine interactions, providing a reproducible framework for future data collection. This paper introduces our dataset and methodology, laying the groundwork for addressing the shortage of spontaneous speech data. We plan to expand this dataset in future stages, offering a growing resource for the research community.

Michael Hassid, Tal Remez, Tu Anh Nguyen et al.

Speech language models (SpeechLMs) process and generate acoustic data only, without textual supervision. In this work, we propose TWIST, a method for training SpeechLMs using a warm-start from a pretrained textual language models. We show using both automatic and human evaluations that TWIST outperforms a cold-start SpeechLM across the board. We empirically analyze the effect of different model design choices such as the speech tokenizer, the pretrained textual model, and the dataset size. We find that model and dataset scale both play an important role in constructing better-performing SpeechLMs. Based on our observations, we present the largest (to the best of our knowledge) SpeechLM both in terms of number of parameters and training data. We additionally introduce two spoken versions of the StoryCloze textual benchmark to further improve model evaluation and advance future research in the field. We make speech samples, code and models publicly available: https://pages.cs.huji.ac.il/adiyoss-lab/twist/ .

Tu Anh Nguyen, Eugene Kharitonov, Jade Copet et al.

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.

Maartje ter Hoeve, Evgeny Kharitonov, Dieuwke Hupkes et al.

Interaction between caregivers and children plays a critical role in human language acquisition and development. Given this observation, it is remarkable that explicit interaction plays little to no role in artificial language modeling -- which also targets the acquisition of human language, yet by artificial models. Moreover, an interactive approach to language modeling has the potential to make language models substantially more versatile and to considerably impact downstream applications. Motivated by these considerations, we pioneer the space of interactive language modeling. As a first contribution we present a road map in which we detail the steps that need to be taken towards interactive language modeling. We then lead by example and take the first steps on this road map, showing the initial feasibility of our approach. As such, this work aims to be the start of a larger research agenda on interactive language modeling.

Felix Kreuk, Adam Polyak, Jade Copet et al.

Speech emotion conversion is the task of modifying the perceived emotion of a speech utterance while preserving the lexical content and speaker identity. In this study, we cast the problem of emotion conversion as a spoken language translation task. We use a decomposition of the speech signal into discrete learned representations, consisting of phonetic-content units, prosodic features, speaker, and emotion. First, we modify the speech content by translating the phonetic-content units to a target emotion, and then predict the prosodic features based on these units. Finally, the speech waveform is generated by feeding the predicted representations into a neural vocoder. Such a paradigm allows us to go beyond spectral and parametric changes of the signal, and model non-verbal vocalizations, such as laughter insertion, yawning removal, etc. We demonstrate objectively and subjectively that the proposed method is vastly superior to current approaches and even beats text-based systems in terms of perceived emotion and audio quality. We rigorously evaluate all components of such a complex system and conclude with an extensive model analysis and ablation study to better emphasize the architectural choices, strengths and weaknesses of the proposed method. Samples are available under the following link: https://speechbot.github.io/emotion.

Afra Alishahi, Grzegorz Chrupała, Alejandrina Cristia et al.

We present the visually-grounded language modelling track that was introduced in the Zero-Resource Speech challenge, 2021 edition, 2nd round. We motivate the new track and discuss participation rules in detail. We also present the two baseline systems that were developed for this track.