Juan Pino

Seamless Communication, Loïc Barrault, Yu-An Chung et al. · meta-ai, mit

What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages? While recent breakthroughs in text-based models have pushed machine translation coverage beyond 200 languages, unified speech-to-speech translation models have yet to achieve similar strides. More specifically, conventional speech-to-speech translation systems rely on cascaded systems that perform translation progressively, putting high-performing unified systems out of reach. To address these gaps, we introduce SeamlessM4T, a single model that supports speech-to-speech translation, speech-to-text translation, text-to-speech translation, text-to-text translation, and automatic speech recognition for up to 100 languages. To build this, we used 1 million hours of open speech audio data to learn self-supervised speech representations with w2v-BERT 2.0. Subsequently, we created a multimodal corpus of automatically aligned speech translations. Filtered and combined with human-labeled and pseudo-labeled data, we developed the first multilingual system capable of translating from and into English for both speech and text. On FLEURS, SeamlessM4T sets a new standard for translations into multiple target languages, achieving an improvement of 20% BLEU over the previous SOTA in direct speech-to-text translation. Compared to strong cascaded models, SeamlessM4T improves the quality of into-English translation by 1.3 BLEU points in speech-to-text and by 2.6 ASR-BLEU points in speech-to-speech. Tested for robustness, our system performs better against background noises and speaker variations in speech-to-text tasks compared to the current SOTA model. Critically, we evaluated SeamlessM4T on gender bias and added toxicity to assess translation safety. Finally, all contributions in this work are open-sourced and accessible at https://github.com/facebookresearch/seamless_communication

Brian Yan, Jiatong Shi, Yun Tang et al. · cmu, nvidia

ESPnet-ST-v2 is a revamp of the open-source ESPnet-ST toolkit necessitated by the broadening interests of the spoken language translation community. ESPnet-ST-v2 supports 1) offline speech-to-text translation (ST), 2) simultaneous speech-to-text translation (SST), and 3) offline speech-to-speech translation (S2ST) -- each task is supported with a wide variety of approaches, differentiating ESPnet-ST-v2 from other open source spoken language translation toolkits. This toolkit offers state-of-the-art architectures such as transducers, hybrid CTC/attention, multi-decoders with searchable intermediates, time-synchronous blockwise CTC/attention, Translatotron models, and direct discrete unit models. In this paper, we describe the overall design, example models for each task, and performance benchmarking behind ESPnet-ST-v2, which is publicly available at https://github.com/espnet/espnet.

Peng-Jen Chen, Kevin Tran, Yilin Yang et al. · meta-ai

We study speech-to-speech translation (S2ST) that translates speech from one language into another language and focuses on building systems to support languages without standard text writing systems. We use English-Taiwanese Hokkien as a case study, and present an end-to-end solution from training data collection, modeling choices to benchmark dataset release. First, we present efforts on creating human annotated data, automatically mining data from large unlabeled speech datasets, and adopting pseudo-labeling to produce weakly supervised data. On the modeling, we take advantage of recent advances in applying self-supervised discrete representations as target for prediction in S2ST and show the effectiveness of leveraging additional text supervision from Mandarin, a language similar to Hokkien, in model training. Finally, we release an S2ST benchmark set to facilitate future research in this field. The demo can be found at https://huggingface.co/spaces/facebook/Hokkien_Translation .

Mohamed Anwar, Bowen Shi, Vedanuj Goswami et al. · meta-ai

We introduce MuAViC, a multilingual audio-visual corpus for robust speech recognition and robust speech-to-text translation providing 1200 hours of audio-visual speech in 9 languages. It is fully transcribed and covers 6 English-to-X translation as well as 6 X-to-English translation directions. To the best of our knowledge, this is the first open benchmark for audio-visual speech-to-text translation and the largest open benchmark for multilingual audio-visual speech recognition. Our baseline results show that MuAViC is effective for building noise-robust speech recognition and translation models. We make the corpus available at https://github.com/facebookresearch/muavic.

Phuong-Hang Le, Hongyu Gong, Changhan Wang et al. · meta-ai

The gap between speech and text modalities is a major challenge in speech-to-text translation (ST). Different methods have been proposed to reduce this gap, but most of them require architectural changes in ST training. In this work, we propose to mitigate this issue at the pre-training stage, requiring no change in the ST model. First, we show that the connectionist temporal classification (CTC) loss can reduce the modality gap by design. We provide a quantitative comparison with the more common cross-entropy loss, showing that pre-training with CTC consistently achieves better final ST accuracy. Nevertheless, CTC is only a partial solution and thus, in our second contribution, we propose a novel pre-training method combining CTC and optimal transport to further reduce this gap. Our method pre-trains a Siamese-like model composed of two encoders, one for acoustic inputs and the other for textual inputs, such that they produce representations that are close to each other in the Wasserstein space. Extensive experiments on the standard CoVoST-2 and MuST-C datasets show that our pre-training method applied to the vanilla encoder-decoder Transformer achieves state-of-the-art performance under the no-external-data setting, and performs on par with recent strong multi-task learning systems trained with external data. Finally, our method can also be applied on top of these multi-task systems, leading to further improvements for these models. Code and pre-trained models are available at https://github.com/formiel/fairseq.

Hirofumi Inaguma, Sravya Popuri, Ilia Kulikov et al. · meta-ai

Direct speech-to-speech translation (S2ST), in which all components can be optimized jointly, is advantageous over cascaded approaches to achieve fast inference with a simplified pipeline. We present a novel two-pass direct S2ST architecture, UnitY, which first generates textual representations and predicts discrete acoustic units subsequently. We enhance the model performance by subword prediction in the first-pass decoder, advanced two-pass decoder architecture design and search strategy, and better training regularization. To leverage large amounts of unlabeled text data, we pre-train the first-pass text decoder based on the self-supervised denoising auto-encoding task. Experimental evaluations on benchmark datasets at various data scales demonstrate that UnitY outperforms a single-pass speech-to-unit translation model by 2.5-4.2 ASR-BLEU with 2.83x decoding speed-up. We show that the proposed methods boost the performance even when predicting spectrogram in the second pass. However, predicting discrete units achieves 2.51x decoding speed-up compared to that case.

Yun Tang, Hongyu Gong, Ning Dong et al. · meta-ai

We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality learning. A self-supervised speech subtask leverages unlabelled speech data, and a (self-)supervised text to text subtask makes use of abundant text training data. Two auxiliary supervised speech tasks are included to unify speech and text modeling space. Our contribution lies in integrating linguistic information from the text corpus into the speech pre-training. Detailed analysis reveals learning interference among subtasks. Two pre-training configurations for speech translation and recognition, respectively, are presented to alleviate subtask interference. Our experiments show the proposed method can effectively fuse speech and text information into one model. It achieves between 1.7 and 2.3 BLEU improvement above the state of the art on the MuST-C speech translation dataset and comparable WERs to wav2vec 2.0 on the Librispeech speech recognition task.

Sravya Popuri, Peng-Jen Chen, Changhan Wang et al. · meta-ai

Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists little parallel S2ST data, compared to the amount of data available for conventional cascaded systems that consist of automatic speech recognition (ASR), machine translation (MT), and text-to-speech (TTS) synthesis. In this work, we explore self-supervised pre-training with unlabeled speech data and data augmentation to tackle this issue. We take advantage of a recently proposed speech-to-unit translation (S2UT) framework that encodes target speech into discrete representations, and transfer pre-training and efficient partial finetuning techniques that work well for speech-to-text translation (S2T) to the S2UT domain by studying both speech encoder and discrete unit decoder pre-training. Our experiments on Spanish-English translation show that self-supervised pre-training consistently improves model performance compared with multitask learning with an average 6.6-12.1 BLEU gain, and it can be further combined with data augmentation techniques that apply MT to create weakly supervised training data. Audio samples are available at: https://facebookresearch.github.io/speech_translation/enhanced_direct_s2st_units/index.html .

Jiatong Shi, Yun Tang, Ann Lee et al. · meta-ai

It has been known that direct speech-to-speech translation (S2ST) models usually suffer from the data scarcity issue because of the limited existing parallel materials for both source and target speech. Therefore to train a direct S2ST system, previous works usually utilize text-to-speech (TTS) systems to generate samples in the target language by augmenting the data from speech-to-text translation (S2TT). However, there is a limited investigation into how the synthesized target speech would affect the S2ST models. In this work, we analyze the effect of changing synthesized target speech for direct S2ST models. We find that simply combining the target speech from different TTS systems can potentially improve the S2ST performances. Following that, we also propose a multi-task framework that jointly optimizes the S2ST system with multiple targets from different TTS systems. Extensive experiments demonstrate that our proposed framework achieves consistent improvements (2.8 BLEU) over the baselines on the Fisher Spanish-English dataset.

Paul-Ambroise Duquenne, Hongyu Gong, Ning Dong et al. · meta-ai

We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. It contains speech alignments in 136 language pairs with a total of 418 thousand hours of speech. To evaluate the quality of this parallel speech, we train bilingual speech-to-speech translation models on mined data only and establish extensive baseline results on EuroParl-ST, VoxPopuli and FLEURS test sets. Enabled by the multilinguality of SpeechMatrix, we also explore multilingual speech-to-speech translation, a topic which was addressed by few other works. We also demonstrate that model pre-training and sparse scaling using Mixture-of-Experts bring large gains to translation performance. The mined data and models are freely available.

Changhan Wang, Hirofumi Inaguma, Peng-Jen Chen et al. · meta-ai

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue, we study a simple and effective approach to build speech translation systems without labeled data by leveraging recent advances in unsupervised speech recognition, machine translation and speech synthesis, either in a pipeline approach, or to generate pseudo-labels for training end-to-end speech translation models. Furthermore, we present an unsupervised domain adaptation technique for pre-trained speech models which improves the performance of downstream unsupervised speech recognition, especially for low-resource settings. Experiments show that unsupervised speech-to-text translation outperforms the previous unsupervised state of the art by 3.2 BLEU on the Libri-Trans benchmark, on CoVoST 2, our best systems outperform the best supervised end-to-end models (without pre-training) from only two years ago by an average of 5.0 BLEU over five X-En directions. We also report competitive results on MuST-C and CVSS benchmarks.

Yejin Lee, Anna Sun, Basil Hosmer et al. · meta-ai, stanford

Generative artificial intelligence (AI) technology is revolutionizing the computing industry. Not only its applications have broadened to various sectors but also poses new system design and optimization opportunities. The technology is capable of understanding and responding in multiple modalities. However, the advanced capability currently comes with significant system resource demands. To sustainably scale generative AI capabilities to billions of users in the world, inference must be fast and efficient. This paper pinpoints key system design and optimization opportunities by characterizing a family of emerging multi-modal generation models on real systems. Auto-regressive token generation is a critical latency performance bottleneck, typically dominated by GPU idle time. In addition to memory-intensive attention across the generative AI models, linear operations constitute significant inference latency due to the feed forward networks in Transformer-based models. We demonstrate that state-of-the-art optimization levers, spanning from applications to system software and hardware, set a 3.88x better baseline.

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.

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.

Hongyu Gong, Ning Dong, Sravya Popuri et al.

Speech-to-speech translation (S2ST) enables spoken communication between people talking in different languages. Despite a few studies on multilingual S2ST, their focus is the multilinguality on the source side, i.e., the translation from multiple source languages to one target language. We present the first work on multilingual S2ST supporting multiple target languages. Leveraging recent advance in direct S2ST with speech-to-unit and vocoder, we equip these key components with multilingual capability. Speech-to-masked-unit (S2MU) is the multilingual extension of S2U, which applies masking to units which don't belong to the given target language to reduce the language interference. We also propose multilingual vocoder which is trained with language embedding and the auxiliary loss of language identification. On benchmark translation testsets, our proposed multilingual model shows superior performance than bilingual models in the translation from English into $16$ target languages.

Seamless Communication, Loïc Barrault, Yu-An Chung et al. · meta-ai, stanford

Large-scale automatic speech translation systems today lack key features that help machine-mediated communication feel seamless when compared to human-to-human dialogue. In this work, we introduce a family of models that enable end-to-end expressive and multilingual translations in a streaming fashion. First, we contribute an improved version of the massively multilingual and multimodal SeamlessM4T model-SeamlessM4T v2. This newer model, incorporating an updated UnitY2 framework, was trained on more low-resource language data. SeamlessM4T v2 provides the foundation on which our next two models are initiated. SeamlessExpressive enables translation that preserves vocal styles and prosody. Compared to previous efforts in expressive speech research, our work addresses certain underexplored aspects of prosody, such as speech rate and pauses, while also preserving the style of one's voice. As for SeamlessStreaming, our model leverages the Efficient Monotonic Multihead Attention mechanism to generate low-latency target translations without waiting for complete source utterances. As the first of its kind, SeamlessStreaming enables simultaneous speech-to-speech/text translation for multiple source and target languages. To ensure that our models can be used safely and responsibly, we implemented the first known red-teaming effort for multimodal machine translation, a system for the detection and mitigation of added toxicity, a systematic evaluation of gender bias, and an inaudible localized watermarking mechanism designed to dampen the impact of deepfakes. Consequently, we bring major components from SeamlessExpressive and SeamlessStreaming together to form Seamless, the first publicly available system that unlocks expressive cross-lingual communication in real-time. The contributions to this work are publicly released and accessible at https://github.com/facebookresearch/seamless_communication

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.

Changhan Wang, Wei-Ning Hsu, Yossi Adi et al.

This paper presents fairseq S^2, a fairseq extension for speech synthesis. We implement a number of autoregressive (AR) and non-AR text-to-speech models, and their multi-speaker variants. To enable training speech synthesis models with less curated data, a number of preprocessing tools are built and their importance is shown empirically. To facilitate faster iteration of development and analysis, a suite of automatic metrics is included. Apart from the features added specifically for this extension, fairseq S^2 also benefits from the scalability offered by fairseq and can be easily integrated with other state-of-the-art systems provided in this framework. The code, documentation, and pre-trained models are available at https://github.com/pytorch/fairseq/tree/master/examples/speech_synthesis.

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.

Hang Le, Juan Pino, Changhan Wang et al.

We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et al., 2017) but consist of two decoders, each responsible for one task (ASR or ST). Our major contribution lies in how these decoders interact with each other: one decoder can attend to different information sources from the other via a dual-attention mechanism. We propose two variants of these architectures corresponding to two different levels of dependencies between the decoders, called the parallel and cross dual-decoder Transformers, respectively. Extensive experiments on the MuST-C dataset show that our models outperform the previously-reported highest translation performance in the multilingual settings, and outperform as well bilingual one-to-one results. Furthermore, our parallel models demonstrate no trade-off between ASR and ST compared to the vanilla multi-task architecture. Our code and pre-trained models are available at https://github.com/formiel/speech-translation.

Changhan Wang, Yun Tang, Xutai Ma et al.

We introduce fairseq S2T, a fairseq extension for speech-to-text (S2T) modeling tasks such as end-to-end speech recognition and speech-to-text translation. It follows fairseq's careful design for scalability and extensibility. We provide end-to-end workflows from data pre-processing, model training to offline (online) inference. We implement state-of-the-art RNN-based, Transformer-based as well as Conformer-based models and open-source detailed training recipes. Fairseq's machine translation models and language models can be seamlessly integrated into S2T workflows for multi-task learning or transfer learning. Fairseq S2T documentation and examples are available at https://github.com/pytorch/fairseq/tree/master/examples/speech_to_text.

Changhan Wang, Anne Wu, Juan Pino

Speech translation has recently become an increasingly popular topic of research, partly due to the development of benchmark datasets. Nevertheless, current datasets cover a limited number of languages. With the aim to foster research in massive multilingual speech translation and speech translation for low resource language pairs, we release CoVoST 2, a large-scale multilingual speech translation corpus covering translations from 21 languages into English and from English into 15 languages. This represents the largest open dataset available to date from total volume and language coverage perspective. Data sanity checks provide evidence about the quality of the data, which is released under CC0 license. We also provide extensive speech recognition, bilingual and multilingual machine translation and speech translation baselines with open-source implementation.

Francisco Guzmán, Peng-Jen Chen, Myle Ott et al.

For machine translation, a vast majority of language pairs in the world are considered low-resource because they have little parallel data available. Besides the technical challenges of learning with limited supervision, it is difficult to evaluate methods trained on low-resource language pairs because of the lack of freely and publicly available benchmarks. In this work, we introduce the FLoRes evaluation datasets for Nepali-English and Sinhala-English, based on sentences translated from Wikipedia. Compared to English, these are languages with very different morphology and syntax, for which little out-of-domain parallel data is available and for which relatively large amounts of monolingual data are freely available. We describe our process to collect and cross-check the quality of translations, and we report baseline performance using several learning settings: fully supervised, weakly supervised, semi-supervised, and fully unsupervised. Our experiments demonstrate that current state-of-the-art methods perform rather poorly on this benchmark, posing a challenge to the research community working on low-resource MT. Data and code to reproduce our experiments are available at https://github.com/facebookresearch/flores.

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.

HyoJung Han, Mohamed Anwar, Juan Pino et al. · meta-ai

Speech recognition and translation systems perform poorly on noisy inputs, which are frequent in realistic environments. Augmenting these systems with visual signals has the potential to improve robustness to noise. However, audio-visual (AV) data is only available in limited amounts and for fewer languages than audio-only resources. To address this gap, we present XLAVS-R, a cross-lingual audio-visual speech representation model for noise-robust speech recognition and translation in over 100 languages. It is designed to maximize the benefits of limited multilingual AV pre-training data, by building on top of audio-only multilingual pre-training and simplifying existing pre-training schemes. Extensive evaluation on the MuAViC benchmark shows the strength of XLAVS-R on downstream audio-visual speech recognition and translation tasks, where it outperforms the previous state of the art by up to 18.5% WER and 4.7 BLEU given noisy AV inputs, and enables strong zero-shot audio-visual ability with audio-only fine-tuning.

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.

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

Vasu Agrawal, Akinniyi Akinyemi, Kathryn Alvero et al.

Human communication involves a complex interplay of verbal and nonverbal signals, essential for conveying meaning and achieving interpersonal goals. To develop socially intelligent AI technologies, it is crucial to develop models that can both comprehend and generate dyadic behavioral dynamics. To this end, we introduce the Seamless Interaction Dataset, a large-scale collection of over 4,000 hours of face-to-face interaction footage from over 4,000 participants in diverse contexts. This dataset enables the development of AI technologies that understand dyadic embodied dynamics, unlocking breakthroughs in virtual agents, telepresence experiences, and multimodal content analysis tools. We also develop a suite of models that utilize the dataset to generate dyadic motion gestures and facial expressions aligned with human speech. These models can take as input both the speech and visual behavior of their interlocutors. We present a variant with speech from an LLM model and integrations with 2D and 3D rendering methods, bringing us closer to interactive virtual agents. Additionally, we describe controllable variants of our motion models that can adapt emotional responses and expressivity levels, as well as generating more semantically-relevant gestures. Finally, we discuss methods for assessing the quality of these dyadic motion models, which are demonstrating the potential for more intuitive and responsive human-AI interactions.

Yun Tang, Anna Y. Sun, Hirofumi Inaguma et al.

Transducer and Attention based Encoder-Decoder (AED) are two widely used frameworks for speech-to-text tasks. They are designed for different purposes and each has its own benefits and drawbacks for speech-to-text tasks. In order to leverage strengths of both modeling methods, we propose a solution by combining Transducer and Attention based Encoder-Decoder (TAED) for speech-to-text tasks. The new method leverages AED's strength in non-monotonic sequence to sequence learning while retaining Transducer's streaming property. In the proposed framework, Transducer and AED share the same speech encoder. The predictor in Transducer is replaced by the decoder in the AED model, and the outputs of the decoder are conditioned on the speech inputs instead of outputs from an unconditioned language model. The proposed solution ensures that the model is optimized by covering all possible read/write scenarios and creates a matched environment for streaming applications. We evaluate the proposed approach on the \textsc{MuST-C} dataset and the findings demonstrate that TAED performs significantly better than Transducer for offline automatic speech recognition (ASR) and speech-to-text translation (ST) tasks. In the streaming case, TAED outperforms Transducer in the ASR task and one ST direction while comparable results are achieved in another translation direction.

Ann Lee, Hongyu Gong, Paul-Ambroise Duquenne et al.

We present a textless speech-to-speech translation (S2ST) system that can translate speech from one language into another language and can be built without the need of any text data. Different from existing work in the literature, we tackle the challenge in modeling multi-speaker target speech and train the systems with real-world S2ST data. The key to our approach is a self-supervised unit-based speech normalization technique, which finetunes a pre-trained speech encoder with paired audios from multiple speakers and a single reference speaker to reduce the variations due to accents, while preserving the lexical content. With only 10 minutes of paired data for speech normalization, we obtain on average 3.2 BLEU gain when training the S2ST model on the VoxPopuli S2ST dataset, compared to a baseline trained on un-normalized speech target. We also incorporate automatically mined S2ST data and show an additional 2.0 BLEU gain. To our knowledge, we are the first to establish a textless S2ST technique that can be trained with real-world data and works for multiple language pairs. Audio samples are available at https://facebookresearch.github.io/speech_translation/textless_s2st_real_data/index.html .

Arun Babu, Changhan Wang, Andros Tjandra et al.

This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on nearly half a million hours of publicly available speech audio in 128 languages, an order of magnitude more public data than the largest known prior work. Our evaluation covers a wide range of tasks, domains, data regimes and languages, both high and low-resource. On the CoVoST-2 speech translation benchmark, we improve the previous state of the art by an average of 7.4 BLEU over 21 translation directions into English. For speech recognition, XLS-R improves over the best known prior work on BABEL, MLS, CommonVoice as well as VoxPopuli, lowering error rates by 14-34% relative on average. XLS-R also sets a new state of the art on VoxLingua107 language identification. Moreover, we show that with sufficient model size, cross-lingual pretraining can outperform English-only pretraining when translating English speech into other languages, a setting which favors monolingual pretraining. We hope XLS-R can help to improve speech processing tasks for many more languages of the world.

Xutai Ma, Hongyu Gong, Danni Liu et al.

We present a direct simultaneous speech-to-speech translation (Simul-S2ST) model, Furthermore, the generation of translation is independent from intermediate text representations. Our approach leverages recent progress on direct speech-to-speech translation with discrete units, in which a sequence of discrete representations, instead of continuous spectrogram features, learned in an unsupervised manner, are predicted from the model and passed directly to a vocoder for speech synthesis on-the-fly. We also introduce the variational monotonic multihead attention (V-MMA), to handle the challenge of inefficient policy learning in speech simultaneous translation. The simultaneous policy then operates on source speech features and target discrete units. We carry out empirical studies to compare cascaded and direct approach on the Fisher Spanish-English and MuST-C English-Spanish datasets. Direct simultaneous model is shown to outperform the cascaded model by achieving a better tradeoff between translation quality and latency.

Danni Liu, Changhan Wang, Hongyu Gong et al.

Speech-to-speech translation (S2ST) converts input speech to speech in another language. A challenge of delivering S2ST in real time is the accumulated delay between the translation and speech synthesis modules. While recently incremental text-to-speech (iTTS) models have shown large quality improvements, they typically require additional future text inputs to reach optimal performance. In this work, we minimize the initial waiting time of iTTS by adapting the upstream speech translator to generate high-quality pseudo lookahead for the speech synthesizer. After mitigating the initial delay, we demonstrate that the duration of synthesized speech also plays a crucial role on latency. We formalize this as a latency metric and then present a simple yet effective duration-scaling approach for latency reduction. Our approaches consistently reduce latency by 0.2-0.5 second without sacrificing speech translation quality.

Yun Tang, Hongyu Gong, Xian Li et al.

In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. Our system is built by leveraging transfer learning across modalities, tasks and languages. First, we leverage general-purpose multilingual modules pretrained with large amounts of unlabelled and labelled data. We further enable knowledge transfer from the text task to the speech task by training two tasks jointly. Finally, our multilingual model is finetuned on speech translation task-specific data to achieve the best translation results. Experimental results show our system outperforms the reported systems, including both end-to-end and cascaded based approaches, by a large margin. In some translation directions, our speech translation results evaluated on the public Multilingual TEDx test set are even comparable with the ones from a strong text-to-text translation system, which uses the oracle speech transcripts as input.

Yun Tang, Juan Pino, Xian Li et al.

Pretraining and multitask learning are widely used to improve the speech to text translation performance. In this study, we are interested in training a speech to text translation model along with an auxiliary text to text translation task. We conduct a detailed analysis to understand the impact of the auxiliary task on the primary task within the multitask learning framework. Our analysis confirms that multitask learning tends to generate similar decoder representations from different modalities and preserve more information from the pretrained text translation modules. We observe minimal negative transfer effect between the two tasks and sharing more parameters is helpful to transfer knowledge from the text task to the speech task. The analysis also reveals that the modality representation difference at the top decoder layers is still not negligible, and those layers are critical for the translation quality. Inspired by these findings, we propose three methods to improve translation quality. First, a parameter sharing and initialization strategy is proposed to enhance information sharing between the tasks. Second, a novel attention-based regularization is proposed for the encoders and pulls the representations from different modalities closer. Third, an online knowledge distillation is proposed to enhance the knowledge transfer from the text to the speech task. Our experiments show that the proposed approach improves translation performance by more than 2 BLEU over a strong baseline and achieves state-of-the-art results on the \textsc{MuST-C} English-German, English-French and English-Spanish language pairs.

Ann Lee, Peng-Jen Chen, Changhan Wang et al.

We present a direct speech-to-speech translation (S2ST) model that translates speech from one language to speech in another language without relying on intermediate text generation. We tackle the problem by first applying a self-supervised discrete speech encoder on the target speech and then training a sequence-to-sequence speech-to-unit translation (S2UT) model to predict the discrete representations of the target speech. When target text transcripts are available, we design a joint speech and text training framework that enables the model to generate dual modality output (speech and text) simultaneously in the same inference pass. Experiments on the Fisher Spanish-English dataset show that the proposed framework yields improvement of 6.7 BLEU compared with a baseline direct S2ST model that predicts spectrogram features. When trained without any text transcripts, our model performance is comparable to models that predict spectrograms and are trained with text supervision, showing the potential of our system for translation between unwritten languages. Audio samples are available at https://facebookresearch.github.io/speech_translation/direct_s2st_units/index.html .

Hongyu Gong, Yun Tang, Juan Pino et al.

Multi-head attention has each of the attention heads collect salient information from different parts of an input sequence, making it a powerful mechanism for sequence modeling. Multilingual and multi-domain learning are common scenarios for sequence modeling, where the key challenge is to maximize positive transfer and mitigate negative transfer across languages and domains. In this paper, we find that non-selective attention sharing is sub-optimal for achieving good generalization across all languages and domains. We further propose attention sharing strategies to facilitate parameter sharing and specialization in multilingual and multi-domain sequence modeling. Our approach automatically learns shared and specialized attention heads for different languages and domains to mitigate their interference. Evaluated in various tasks including speech recognition, text-to-text and speech-to-text translation, the proposed attention sharing strategies consistently bring gains to sequence models built upon multi-head attention. For speech-to-text translation, our approach yields an average of $+2.0$ BLEU over $13$ language directions in multilingual setting and $+2.0$ BLEU over $3$ domains in multi-domain setting.

Hang Le, Juan Pino, Changhan Wang et al.

Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting lightweight modules between layers, resulting in the addition of only a small number of task-specific trainable parameters. While adapter tuning was investigated for multilingual neural machine translation, this paper proposes a comprehensive analysis of adapters for multilingual speech translation (ST). Starting from different pre-trained models (a multilingual ST trained on parallel data or a multilingual BART (mBART) trained on non-parallel multilingual data), we show that adapters can be used to: (a) efficiently specialize ST to specific language pairs with a low extra cost in terms of parameters, and (b) transfer from an automatic speech recognition (ASR) task and an mBART pre-trained model to a multilingual ST task. Experiments show that adapter tuning offer competitive results to full fine-tuning, while being much more parameter-efficient.

Changhan Wang, Anne Wu, Juan Pino et al.

In this paper, we improve speech translation (ST) through effectively leveraging large quantities of unlabeled speech and text data in different and complementary ways. We explore both pretraining and self-training by using the large Libri-Light speech audio corpus and language modeling with CommonCrawl. Our experiments improve over the previous state of the art by 2.6 BLEU on average on all four considered CoVoST 2 language pairs via a simple recipe of combining wav2vec 2.0 pretraining, a single iteration of self-training and decoding with a language model. Different to existing work, our approach does not leverage any other supervision than ST data. Code and models will be publicly released.

Xutai Ma, Juan Pino, Philipp Koehn

Simultaneous text translation and end-to-end speech translation have recently made great progress but little work has combined these tasks together. We investigate how to adapt simultaneous text translation methods such as wait-k and monotonic multihead attention to end-to-end simultaneous speech translation by introducing a pre-decision module. A detailed analysis is provided on the latency-quality trade-offs of combining fixed and flexible pre-decision with fixed and flexible policies. We also design a novel computation-aware latency metric, adapted from Average Lagging.

Xutai Ma, Yongqiang Wang, Mohammad Javad Dousti et al.

Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios since self-attention is computed over an entire input sequence and the computational cost grows quadratically with the length of the input sequence. Nevertheless, most of the previous work on simultaneous speech translation, the task of generating translations from partial audio input, ignores the time spent in generating the translation when analyzing the latency. With this assumption, a system may have good latency quality trade-offs but be inapplicable in real-time scenarios. In this paper, we focus on the task of streaming simultaneous speech translation, where the systems are not only capable of translating with partial input but are also able to handle very long or continuous input. We propose an end-to-end transformer-based sequence-to-sequence model, equipped with an augmented memory transformer encoder, which has shown great success on the streaming automatic speech recognition task with hybrid or transducer-based models. We conduct an empirical evaluation of the proposed model on segment, context and memory sizes and we compare our approach to a transformer with a unidirectional mask.

Xian Li, Changhan Wang, Yun Tang et al.

We present a simple yet effective approach to build multilingual speech-to-text (ST) translation by efficient transfer learning from pretrained speech encoder and text decoder. Our key finding is that a minimalistic LNA (LayerNorm and Attention) finetuning can achieve zero-shot crosslingual and cross-modality transfer ability by only finetuning less than 10% of the pretrained parameters. This enables effectively leveraging large pretrained models with low training cost. Using wav2vec 2.0 for acoustic modeling, and mBART for multilingual text generation, our approach advanced the new state-of-the-art for 34 translation directions (and surpassing cascaded ST for 23 of them) on large-scale multilingual ST benchmark CoVoST 2 (+6.4 BLEU on average across 15 En-X directions and +5.1 BLEU on average across 19 X-En directions). Our approach demonstrates strong zero-shot performance in a many-to-many multilingual model (+5.7 BLEU on average across 18 non-English directions), making it an appealing approach for attaining high-quality speech translation with improved parameter and data efficiency.

Yun Tang, Juan Pino, Changhan Wang et al.

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data. This presents a challenge for speech applications where labelled speech data is very expensive to obtain, such as automatic speech recognition (ASR) and speech translation (ST). In this study, we propose a general multi-task learning framework to leverage text data for ASR and ST tasks. Two auxiliary tasks, a denoising autoencoder task and machine translation task, are proposed to be co-trained with ASR and ST tasks respectively. We demonstrate that representing text input as phoneme sequences can reduce the difference between speech and text inputs, and enhance the knowledge transfer from text corpora to the speech to text tasks. Our experiments show that the proposed method achieves a relative 10~15% word error rate reduction on the English Librispeech task compared with our baseline, and improves the speech translation quality on the MuST-C tasks by 3.6~9.2 BLEU.

Xutai Ma, Mohammad Javad Dousti, Changhan Wang et al.

Simultaneous translation on both text and speech focuses on a real-time and low-latency scenario where the model starts translating before reading the complete source input. Evaluating simultaneous translation models is more complex than offline models because the latency is another factor to consider in addition to translation quality. The research community, despite its growing focus on novel modeling approaches to simultaneous translation, currently lacks a universal evaluation procedure. Therefore, we present SimulEval, an easy-to-use and general evaluation toolkit for both simultaneous text and speech translation. A server-client scheme is introduced to create a simultaneous translation scenario, where the server sends source input and receives predictions for evaluation and the client executes customized policies. Given a policy, it automatically performs simultaneous decoding and collectively reports several popular latency metrics. We also adapt latency metrics from text simultaneous translation to the speech task. Additionally, SimulEval is equipped with a visualization interface to provide better understanding of the simultaneous decoding process of a system. SimulEval has already been extensively used for the IWSLT 2020 shared task on simultaneous speech translation. Code will be released upon publication.

Anne Wu, Changhan Wang, Juan Pino et al.

End-to-end speech-to-text translation can provide a simpler and smaller system but is facing the challenge of data scarcity. Pre-training methods can leverage unlabeled data and have been shown to be effective on data-scarce settings. In this work, we explore whether self-supervised pre-trained speech representations can benefit the speech translation task in both high- and low-resource settings, whether they can transfer well to other languages, and whether they can be effectively combined with other common methods that help improve low-resource end-to-end speech translation such as using a pre-trained high-resource speech recognition system. We demonstrate that self-supervised pre-trained features can consistently improve the translation performance, and cross-lingual transfer allows to extend to a variety of languages without or with little tuning.

Changhan Wang, Juan Pino, Jiatao Gu

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share the language modeling (decoder) for the same language, which is likely to be inefficient for distant target languages. We introduce speech-to-text translation (ST) as an auxiliary task to incorporate additional knowledge of the target language and enable transferring from that target language. Specifically, we first translate high-resource ASR transcripts into a target low-resource language, with which a ST model is trained. Both ST and target ASR share the same attention-based encoder-decoder architecture and vocabulary. The former task then provides a fully pre-trained model for the latter, bringing up to 24.6% word error rate (WER) reduction to the baseline (direct transfer from high-resource ASR). We show that training ST with human translations is not necessary. ST trained with machine translation (MT) pseudo-labels brings consistent gains. It can even outperform those using human labels when transferred to target ASR by leveraging only 500K MT examples. Even with pseudo-labels from low-resource MT (200K examples), ST-enhanced transfer brings up to 8.9% WER reduction to direct transfer.

Juan Pino, Qiantong Xu, Xutai Ma et al.

One of the main challenges for end-to-end speech translation is data scarcity. We leverage pseudo-labels generated from unlabeled audio by a cascade and an end-to-end speech translation model. This provides 8.3 and 5.7 BLEU gains over a strong semi-supervised baseline on the MuST-C English-French and English-German datasets, reaching state-of-the art performance. The effect of the quality of the pseudo-labels is investigated. Our approach is shown to be more effective than simply pre-training the encoder on the speech recognition task. Finally, we demonstrate the effectiveness of self-training by directly generating pseudo-labels with an end-to-end model instead of a cascade model.

Arya D. McCarthy, Liezl Puzon, Juan Pino

We propose autoencoding speaker conversion for training data augmentation in automatic speech translation. This technique directly transforms an audio sequence, resulting in audio synthesized to resemble another speaker's voice. Our method compares favorably to SpecAugment on English$\to$French and English$\to$Romanian automatic speech translation (AST) tasks as well as on a low-resource English automatic speech recognition (ASR) task. Further, in ablations, we show the benefits of both quantity and diversity in augmented data. Finally, we show that we can combine our approach with augmentation by machine-translated transcripts to obtain a competitive end-to-end AST model that outperforms a very strong cascade model on an English$\to$French AST task. Our method is sufficiently general that it can be applied to other speech generation and analysis tasks.

Changhan Wang, Juan Pino, Anne Wu et al.

Spoken language translation has recently witnessed a resurgence in popularity, thanks to the development of end-to-end models and the creation of new corpora, such as Augmented LibriSpeech and MuST-C. Existing datasets involve language pairs with English as a source language, involve very specific domains or are low resource. We introduce CoVoST, a multilingual speech-to-text translation corpus from 11 languages into English, diversified with over 11,000 speakers and over 60 accents. We describe the dataset creation methodology and provide empirical evidence of the quality of the data. We also provide initial benchmarks, including, to our knowledge, the first end-to-end many-to-one multilingual models for spoken language translation. CoVoST is released under CC0 license and free to use. We also provide additional evaluation data derived from Tatoeba under CC licenses.

Xutai Ma, Juan Pino, James Cross et al.

Simultaneous machine translation models start generating a target sequence before they have encoded or read the source sequence. Recent approaches for this task either apply a fixed policy on a state-of-the art Transformer model, or a learnable monotonic attention on a weaker recurrent neural network-based structure. In this paper, we propose a new attention mechanism, Monotonic Multihead Attention (MMA), which extends the monotonic attention mechanism to multihead attention. We also introduce two novel and interpretable approaches for latency control that are specifically designed for multiple attentions heads. We apply MMA to the simultaneous machine translation task and demonstrate better latency-quality tradeoffs compared to MILk, the previous state-of-the-art approach. We also analyze how the latency controls affect the attention span and we motivate the introduction of our model by analyzing the effect of the number of decoder layers and heads on quality and latency.