Yu-An Chung

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

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 .

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.

Heng-Jui Chang, Ning Dong, Ruslan Mavlyutov et al. · mit

Large-scale self-supervised pre-trained speech encoders outperform conventional approaches in speech recognition and translation tasks. Due to the high cost of developing these large models, building new encoders for new tasks and deploying them to on-device applications are infeasible. Prior studies propose model compression methods to address this issue, but those works focus on smaller models and less realistic tasks. Thus, we propose Contrastive Layer-to-layer Distillation (CoLLD), a novel knowledge distillation method to compress pre-trained speech encoders by leveraging masked prediction and contrastive learning to train student models to copy the behavior of a large teacher model. CoLLD outperforms prior methods and closes the gap between small and large models on multilingual speech-to-text translation and recognition benchmarks.

Omnilingual SONAR Team, João Maria Janeiro, Pere-Lluís Huguet Cabot et al. · meta-ai

Cross-lingual sentence encoders typically cover only a few hundred languages and often trade downstream quality for stronger alignment, limiting their adoption. We introduce OmniSONAR, a new family of omnilingual, cross-lingual and cross-modal sentence embedding models that natively embed text, speech, code, and mathematical expressions in a single semantic space, while delivering state-of-the-art downstream performance at the scale of thousands of languages, from high-resource to extremely low-resource varieties. To reach this scale without representation collapse, we use progressive training. We first learn a strong foundational space for 200 languages with an LLM-initialized encoder-decoder, combining token-level decoding with a novel split-softmax contrastive loss and synthetic hard negatives. Building on this foundation, we expand to several thousands language varieties via a two-stage teacher-student encoder distillation framework. Finally, we demonstrate the cross-modal extensibility of this space by seamlessly mapping 177 spoken languages into it. OmniSONAR halves cross-lingual similarity search error on the 200-language FLORES dataset and reduces error by a factor of 15 on the 1,560-language BIBLE benchmark. It also enables strong translation, outperforming NLLB-3B on multilingual benchmarks and exceeding prior models (including much larger LLMs) by 15 chrF++ points on 1,560 languages into English BIBLE translation. OmniSONAR also performs strongly on MTEB and XLCoST. For speech, OmniSONAR achieves a 43% lower similarity-search error and reaches 97% of SeamlessM4T speech-to-text quality, despite being zero-shot for translation (trained only on ASR data). Finally, by training an encoder-decoder LM, Spectrum, exclusively on English text processing OmniSONAR embedding sequences, we unlock high-performance transfer to thousands of languages and speech for complex downstream tasks.

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.

Omnilingual ASR team, Gil Keren, Artyom Kozhevnikov et al.

Automatic speech recognition (ASR) has advanced in high-resource languages, but most of the world's 7,000+ languages remain unsupported, leaving thousands of long-tail languages behind. Expanding ASR coverage has been costly and limited by architectures that restrict language support, making extension inaccessible to most--all while entangled with ethical concerns when pursued without community collaboration. To transcend these limitations, we introduce Omnilingual ASR, the first large-scale ASR system designed for extensibility. Omnilingual ASR enables communities to introduce unserved languages with only a handful of data samples. It scales self-supervised pre-training to 7B parameters to learn robust speech representations and introduces an encoder-decoder architecture designed for zero-shot generalization, leveraging a LLM-inspired decoder. This capability is grounded in a massive and diverse training corpus; by combining breadth of coverage with linguistic variety, the model learns representations robust enough to adapt to unseen languages. Incorporating public resources with community-sourced recordings gathered through compensated local partnerships, Omnilingual ASR expands coverage to over 1,600 languages, the largest such effort to date--including over 500 never before served by ASR. Automatic evaluations show substantial gains over prior systems, especially in low-resource conditions, and strong generalization. We release Omnilingual ASR as a family of models, from 300M variants for low-power devices to 7B for maximum accuracy. We reflect on the ethical considerations shaping this design and conclude by discussing its societal impact. In particular, we highlight how open-sourcing models and tools can lower barriers for researchers and communities, inviting new forms of participation. Open-source artifacts are available at https://github.com/facebookresearch/omnilingual-asr.

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

Peter J. Liu, Yu-An Chung, Jie Ren

We propose an end-to-end neural model for zero-shot abstractive text summarization of paragraphs, and introduce a benchmark task, ROCSumm, based on ROCStories, a subset for which we collected human summaries. In this task, five-sentence stories (paragraphs) are summarized with one sentence, using human summaries only for evaluation. We show results for extractive and human baselines to demonstrate a large abstractive gap in performance. Our model, SummAE, consists of a denoising auto-encoder that embeds sentences and paragraphs in a common space, from which either can be decoded. Summaries for paragraphs are generated by decoding a sentence from the paragraph representations. We find that traditional sequence-to-sequence auto-encoders fail to produce good summaries and describe how specific architectural choices and pre-training techniques can significantly improve performance, outperforming extractive baselines. The data, training, evaluation code, and best model weights are open-sourced.

Yao-Yuan Yang, Shao-Chuan Lee, Yu-An Chung et al.

libact is a Python package designed to make active learning easier for general users. The package not only implements several popular active learning strategies, but also features the active-learning-by-learning meta-algorithm that assists the users to automatically select the best strategy on the fly. Furthermore, the package provides a unified interface for implementing more strategies, models and application-specific labelers. The package is open-source on Github, and can be easily installed from Python Package Index repository.

Heng-Jui Chang, Hongyu Gong, Changhan Wang et al. · mit

Spoken language models (SLMs) have gained increasing attention with advancements in text-based, decoder-only language models. SLMs process text and speech, enabling simultaneous speech understanding and generation. This paper presents Double-Codebook Speaker-invariant Clustering (DC-Spin), which aims to improve speech tokenization by bridging audio signals and SLM tokens. DC-Spin extracts speaker-invariant tokens rich in phonetic information and resilient to input variations, enhancing zero-shot SLM tasks and speech resynthesis. We propose a chunk-wise approach to enable streamable DC-Spin without retraining and degradation. Comparisons of tokenization methods (self-supervised and neural audio codecs), model scalability, and downstream task proxies show that tokens easily modeled by an n-gram LM or aligned with phonemes offer strong performance, providing insights for designing speech tokenizers for SLMs.

Ankur Bapna, Yu-an Chung, Nan Wu et al.

Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been hugely successful when fine-tuned on downstream tasks from a variety of domains and languages. This paper takes the universality of unsupervised language pre-training one step further, by unifying speech and text pre-training within a single model. We build a single encoder with the BERT objective on unlabeled text together with the w2v-BERT objective on unlabeled speech. To further align our model representations across modalities, we leverage alignment losses, specifically Translation Language Modeling (TLM) and Speech Text Matching (STM) that make use of supervised speech-text recognition data. We demonstrate that incorporating both speech and text data during pre-training can significantly improve downstream quality on CoVoST~2 speech translation, by around 1 BLEU compared to single-modality pre-trained models, while retaining close to SotA performance on LibriSpeech and SpeechStew ASR tasks. On four GLUE tasks and text-normalization, we observe evidence of capacity limitations and interference between the two modalities, leading to degraded performance compared to an equivalent text-only model, while still being competitive with BERT. Through extensive empirical analysis we also demonstrate the importance of the choice of objective function for speech pre-training, and the beneficial effect of adding additional supervised signals on the quality of the learned representations.

Yuan Gong, Cheng-I Jeff Lai, Yu-An Chung et al.

Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending the success of Transformers, which were originally developed for language processing, to the vision domain. A recent study showed that a similar methodology can also be applied to the audio domain. Specifically, the Audio Spectrogram Transformer (AST) achieves state-of-the-art results on various audio classification benchmarks. However, pure Transformer models tend to require more training data compared to CNNs, and the success of the AST relies on supervised pretraining that requires a large amount of labeled data and a complex training pipeline, thus limiting the practical usage of AST. This paper focuses on audio and speech classification, and aims to reduce the need for large amounts of labeled data for AST by leveraging self-supervised learning using unlabeled data. Specifically, we propose to pretrain the AST model with joint discriminative and generative masked spectrogram patch modeling (MSPM) using unlabeled audio from AudioSet and Librispeech. We evaluate our pretrained models on both audio and speech classification tasks including audio event classification, keyword spotting, emotion recognition, and speaker identification. The proposed self-supervised framework significantly boosts AST performance on all tasks, with an average improvement of 60.9%, leading to similar or even better results than a supervised pretrained AST. To the best of our knowledge, it is the first patch-based self-supervised learning framework in the audio and speech domain, and also the first self-supervised learning framework for AST.

Yu-An Chung, Yu Zhang, Wei Han et al.

Motivated by the success of masked language modeling~(MLM) in pre-training natural language processing models, we propose w2v-BERT that explores MLM for self-supervised speech representation learning. w2v-BERT is a framework that combines contrastive learning and MLM, where the former trains the model to discretize input continuous speech signals into a finite set of discriminative speech tokens, and the latter trains the model to learn contextualized speech representations via solving a masked prediction task consuming the discretized tokens. In contrast to existing MLM-based speech pre-training frameworks such as HuBERT, which relies on an iterative re-clustering and re-training process, or vq-wav2vec, which concatenates two separately trained modules, w2v-BERT can be optimized in an end-to-end fashion by solving the two self-supervised tasks~(the contrastive task and MLM) simultaneously. Our experiments show that w2v-BERT achieves competitive results compared to current state-of-the-art pre-trained models on the LibriSpeech benchmarks when using the Libri-Light~60k corpus as the unsupervised data. In particular, when compared to published models such as conformer-based wav2vec~2.0 and HuBERT, our model shows~5\% to~10\% relative WER reduction on the test-clean and test-other subsets. When applied to the Google's Voice Search traffic dataset, w2v-BERT outperforms our internal conformer-based wav2vec~2.0 by more than~30\% relatively.

Yuan Gong, Yu-An Chung, James Glass

In the past decade, convolutional neural networks (CNNs) have been widely adopted as the main building block for end-to-end audio classification models, which aim to learn a direct mapping from audio spectrograms to corresponding labels. To better capture long-range global context, a recent trend is to add a self-attention mechanism on top of the CNN, forming a CNN-attention hybrid model. However, it is unclear whether the reliance on a CNN is necessary, and if neural networks purely based on attention are sufficient to obtain good performance in audio classification. In this paper, we answer the question by introducing the Audio Spectrogram Transformer (AST), the first convolution-free, purely attention-based model for audio classification. We evaluate AST on various audio classification benchmarks, where it achieves new state-of-the-art results of 0.485 mAP on AudioSet, 95.6% accuracy on ESC-50, and 98.1% accuracy on Speech Commands V2.

Yuan Gong, Yu-An Chung, James Glass

Audio tagging is an active research area and has a wide range of applications. Since the release of AudioSet, great progress has been made in advancing model performance, which mostly comes from the development of novel model architectures and attention modules. However, we find that appropriate training techniques are equally important for building audio tagging models with AudioSet, but have not received the attention they deserve. To fill the gap, in this work, we present PSLA, a collection of training techniques that can noticeably boost the model accuracy including ImageNet pretraining, balanced sampling, data augmentation, label enhancement, model aggregation and their design choices. By training an EfficientNet with these techniques, we obtain a single model (with 13.6M parameters) and an ensemble model that achieve mean average precision (mAP) scores of 0.444 and 0.474 on AudioSet, respectively, outperforming the previous best system of 0.439 with 81M parameters. In addition, our model also achieves a new state-of-the-art mAP of 0.567 on FSD50K.

Alexander H. Liu, Yu-An Chung, James Glass

Self-supervised speech representations have been shown to be effective in a variety of speech applications. However, existing representation learning methods generally rely on the autoregressive model and/or observed global dependencies while generating the representation. In this work, we propose Non-Autoregressive Predictive Coding (NPC), a self-supervised method, to learn a speech representation in a non-autoregressive manner by relying only on local dependencies of speech. NPC has a conceptually simple objective and can be implemented easily with the introduced Masked Convolution Blocks. NPC offers a significant speedup for inference since it is parallelizable in time and has a fixed inference time for each time step regardless of the input sequence length. We discuss and verify the effectiveness of NPC by theoretically and empirically comparing it with other methods. We show that the NPC representation is comparable to other methods in speech experiments on phonetic and speaker classification while being more efficient.

Yu-An Chung, Yonatan Belinkov, James Glass

Self-supervised speech representation learning has recently been a prosperous research topic. Many algorithms have been proposed for learning useful representations from large-scale unlabeled data, and their applications to a wide range of speech tasks have also been investigated. However, there has been little research focusing on understanding the properties of existing approaches. In this work, we aim to provide a comparative study of some of the most representative self-supervised algorithms. Specifically, we quantify the similarities between different self-supervised representations using existing similarity measures. We also design probing tasks to study the correlation between the models' pre-training loss and the amount of specific speech information contained in their learned representations. In addition to showing how various self-supervised models behave differently given the same input, our study also finds that the training objective has a higher impact on representation similarity than architectural choices such as building blocks (RNN/Transformer/CNN) and directionality (uni/bidirectional). Our results also suggest that there exists a strong correlation between pre-training loss and downstream performance for some self-supervised algorithms.

Yu-An Chung, Chenguang Zhu, Michael Zeng

Spoken language understanding (SLU) requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. To boost the models' performance, various pre-training methods have been proposed to learn rich representations from large-scale unannotated speech and text. However, the inherent disparities between the two modalities necessitate a mutual analysis. In this paper, we propose a novel semi-supervised learning framework, SPLAT, to jointly pre-train the speech and language modules. Besides conducting a self-supervised masked language modeling task on the two individual modules using unpaired speech and text, SPLAT aligns representations from the two modules in a shared latent space using a small amount of paired speech and text. Thus, during fine-tuning, the speech module alone can produce representations carrying both acoustic information and contextual semantic knowledge of an input acoustic signal. Experimental results verify the effectiveness of our approach on various SLU tasks. For example, SPLAT improves the previous state-of-the-art performance on the Spoken SQuAD dataset by more than 10%.

Yu-An Chung, Hao Tang, James Glass

Autoregressive Predictive Coding (APC), as a self-supervised objective, has enjoyed success in learning representations from large amounts of unlabeled data, and the learned representations are rich for many downstream tasks. However, the connection between low self-supervised loss and strong performance in downstream tasks remains unclear. In this work, we propose Vector-Quantized Autoregressive Predictive Coding (VQ-APC), a novel model that produces quantized representations, allowing us to explicitly control the amount of information encoded in the representations. By studying a sequence of increasingly limited models, we reveal the constituents of the learned representations. In particular, we confirm the presence of information with probing tasks, while showing the absence of information with mutual information, uncovering the model's preference in preserving speech information as its capacity becomes constrained. We find that there exists a point where phonetic and speaker information are amplified to maximize a self-supervised objective. As a byproduct, the learned codes for a particular model capacity correspond well to English phones.

Yu-An Chung, James Glass

Training objectives based on predictive coding have recently been shown to be very effective at learning meaningful representations from unlabeled speech. One example is Autoregressive Predictive Coding (Chung et al., 2019), which trains an autoregressive RNN to generate an unseen future frame given a context such as recent past frames. The basic hypothesis of these approaches is that hidden states that can accurately predict future frames are a useful representation for many downstream tasks. In this paper we extend this hypothesis and aim to enrich the information encoded in the hidden states by training the model to make more accurate future predictions. We propose an auxiliary objective that serves as a regularization to improve generalization of the future frame prediction task. Experimental results on phonetic classification, speech recognition, and speech translation not only support the hypothesis, but also demonstrate the effectiveness of our approach in learning representations that contain richer phonetic content.

Wei-Hung Weng, Yu-An Chung, Schrasing Tong

In the era of clinical information explosion, a good strategy for clinical text summarization is helpful to improve the clinical workflow. The ideal summarization strategy can preserve important information in the informative but less organized, ill-structured clinical narrative texts. Instead of using pure statistical learning approaches, which are difficult to interpret and explain, we utilized knowledge of computational linguistics with human experts-curated biomedical knowledge base to achieve the interpretable and meaningful clinical text summarization. Our research objective is to use the biomedical ontology with semantic information, and take the advantage from the language hierarchical structure, the constituency tree, in order to identify the correct clinical concepts and the corresponding negation information, which is critical for summarizing clinical concepts from narrative text. We achieved the clinically acceptable performance for both negation detection and concept identification, and the clinical concepts with common negated patterns can be identified and negated by the proposed method.

Yu-An Chung, James Glass

Learning meaningful and general representations from unannotated speech that are applicable to a wide range of tasks remains challenging. In this paper we propose to use autoregressive predictive coding (APC), a recently proposed self-supervised objective, as a generative pre-training approach for learning meaningful, non-specific, and transferable speech representations. We pre-train APC on large-scale unlabeled data and conduct transfer learning experiments on three speech applications that require different information about speech characteristics to perform well: speech recognition, speech translation, and speaker identification. Extensive experiments show that APC not only outperforms surface features (e.g., log Mel spectrograms) and other popular representation learning methods on all three tasks, but is also effective at reducing downstream labeled data size and model parameters. We also investigate the use of Transformers for modeling APC and find it superior to RNNs.

Wei Fang, Yu-An Chung, James Glass

Modern text-to-speech (TTS) systems are able to generate audio that sounds almost as natural as human speech. However, the bar of developing high-quality TTS systems remains high since a sizable set of studio-quality <text, audio> pairs is usually required. Compared to commercial data used to develop state-of-the-art systems, publicly available data are usually worse in terms of both quality and size. Audio generated by TTS systems trained on publicly available data tends to not only sound less natural, but also exhibits more background noise. In this work, we aim to lower TTS systems' reliance on high-quality data by providing them the textual knowledge extracted by deep pre-trained language models during training. In particular, we investigate the use of BERT to assist the training of Tacotron-2, a state of the art TTS consisting of an encoder and an attention-based decoder. BERT representations learned from large amounts of unlabeled text data are shown to contain very rich semantic and syntactic information about the input text, and have potential to be leveraged by a TTS system to compensate the lack of high-quality data. We incorporate BERT as a parallel branch to the Tacotron-2 encoder with its own attention head. For an input text, it is simultaneously passed into BERT and the Tacotron-2 encoder. The representations extracted by the two branches are concatenated and then fed to the decoder. As a preliminary study, although we have not found incorporating BERT into Tacotron-2 generates more natural or cleaner speech at a human-perceivable level, we observe improvements in other aspects such as the model is being significantly better at knowing when to stop decoding such that there is much less babbling at the end of the synthesized audio and faster convergence during training.

Yu-An Chung, Wei-Ning Hsu, Hao Tang et al.

This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is designed to preserve information for a wide range of downstream tasks. In addition, the proposed model does not require any phonetic or word boundary labels, allowing the model to benefit from large quantities of unlabeled data. Speech representations learned by our model significantly improve performance on both phone classification and speaker verification over the surface features and other supervised and unsupervised approaches. Further analysis shows that different levels of speech information are captured by our model at different layers. In particular, the lower layers tend to be more discriminative for speakers, while the upper layers provide more phonetic content.

Wei-Hung Weng, Yu-An Chung, Peter Szolovits

As patients' access to their doctors' clinical notes becomes common, translating professional, clinical jargon to layperson-understandable language is essential to improve patient-clinician communication. Such translation yields better clinical outcomes by enhancing patients' understanding of their own health conditions, and thus improving patients' involvement in their own care. Existing research has used dictionary-based word replacement or definition insertion to approach the need. However, these methods are limited by expert curation, which is hard to scale and has trouble generalizing to unseen datasets that do not share an overlapping vocabulary. In contrast, we approach the clinical word and sentence translation problem in a completely unsupervised manner. We show that a framework using representation learning, bilingual dictionary induction and statistical machine translation yields the best precision at 10 of 0.827 on professional-to-consumer word translation, and mean opinion scores of 4.10 and 4.28 out of 5 for clinical correctness and layperson readability, respectively, on sentence translation. Our fully-unsupervised strategy overcomes the curation problem, and the clinically meaningful evaluation reduces biases from inappropriate evaluators, which are critical in clinical machine learning.

Yu-An Chung, Wei-Hung Weng, Schrasing Tong et al.

We present a framework for building speech-to-text translation (ST) systems using only monolingual speech and text corpora, in other words, speech utterances from a source language and independent text from a target language. As opposed to traditional cascaded systems and end-to-end architectures, our system does not require any labeled data (i.e., transcribed source audio or parallel source and target text corpora) during training, making it especially applicable to language pairs with very few or even zero bilingual resources. The framework initializes the ST system with a cross-modal bilingual dictionary inferred from the monolingual corpora, that maps every source speech segment corresponding to a spoken word to its target text translation. For unseen source speech utterances, the system first performs word-by-word translation on each speech segment in the utterance. The translation is improved by leveraging a language model and a sequence denoising autoencoder to provide prior knowledge about the target language. Experimental results show that our unsupervised system achieves comparable BLEU scores to supervised end-to-end models despite the lack of supervision. We also provide an ablation analysis to examine the utility of each component in our system.

Yu-An Chung, Yuxuan Wang, Wei-Ning Hsu et al.

Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs for training, which are expensive to collect. In this paper, we propose a semi-supervised training framework to improve the data efficiency of Tacotron. The idea is to allow Tacotron to utilize textual and acoustic knowledge contained in large, publicly-available text and speech corpora. Importantly, these external data are unpaired and potentially noisy. Specifically, first we embed each word in the input text into word vectors and condition the Tacotron encoder on them. We then use an unpaired speech corpus to pre-train the Tacotron decoder in the acoustic domain. Finally, we fine-tune the model using available paired data. We demonstrate that the proposed framework enables Tacotron to generate intelligible speech using less than half an hour of paired training data.

Yu-An Chung, Wei-Hung Weng, Schrasing Tong et al.

Recent research has shown that word embedding spaces learned from text corpora of different languages can be aligned without any parallel data supervision. Inspired by the success in unsupervised cross-lingual word embeddings, in this paper we target learning a cross-modal alignment between the embedding spaces of speech and text learned from corpora of their respective modalities in an unsupervised fashion. The proposed framework learns the individual speech and text embedding spaces, and attempts to align the two spaces via adversarial training, followed by a refinement procedure. We show how our framework could be used to perform spoken word classification and translation, and the results on these two tasks demonstrate that the performance of our unsupervised alignment approach is comparable to its supervised counterpart. Our framework is especially useful for developing automatic speech recognition (ASR) and speech-to-text translation systems for low- or zero-resource languages, which have little parallel audio-text data for training modern supervised ASR and speech-to-text translation models, but account for the majority of the languages spoken across the world.

Yu-An Chung, James Glass

In this paper, we propose a novel deep neural network architecture, Speech2Vec, for learning fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic information pertaining to the underlying spoken words, and are close to other vectors in the embedding space if their corresponding underlying spoken words are semantically similar. The proposed model can be viewed as a speech version of Word2Vec. Its design is based on a RNN Encoder-Decoder framework, and borrows the methodology of skipgrams or continuous bag-of-words for training. Learning word embeddings directly from speech enables Speech2Vec to make use of the semantic information carried by speech that does not exist in plain text. The learned word embeddings are evaluated and analyzed on 13 widely used word similarity benchmarks, and outperform word embeddings learned by Word2Vec from the transcriptions.

Yu-An Chung, Wei-Hung Weng

Deep neural networks have been investigated in learning latent representations of medical images, yet most of the studies limit their approach in a single supervised convolutional neural network (CNN), which usually rely heavily on a large scale annotated dataset for training. To learn image representations with less supervision involved, we propose a deep Siamese CNN (SCNN) architecture that can be trained with only binary image pair information. We evaluated the learned image representations on a task of content-based medical image retrieval using a publicly available multiclass diabetic retinopathy fundus image dataset. The experimental results show that our proposed deep SCNN is comparable to the state-of-the-art single supervised CNN, and requires much less supervision for training.

Yu-An Chung, Hung-Yi Lee, James Glass

Although transfer learning has been shown to be successful for tasks like object and speech recognition, its applicability to question answering (QA) has yet to be well-studied. In this paper, we conduct extensive experiments to investigate the transferability of knowledge learned from a source QA dataset to a target dataset using two QA models. The performance of both models on a TOEFL listening comprehension test (Tseng et al., 2016) and MCTest (Richardson et al., 2013) is significantly improved via a simple transfer learning technique from MovieQA (Tapaswi et al., 2016). In particular, one of the models achieves the state-of-the-art on all target datasets; for the TOEFL listening comprehension test, it outperforms the previous best model by 7%. Finally, we show that transfer learning is helpful even in unsupervised scenarios when correct answers for target QA dataset examples are not available.

Yu-An Chung, James Glass

In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic information pertaining to the segments, and are close to other vectors in the embedding space if their corresponding segments are semantically similar. The design of the proposed model is based on the RNN Encoder-Decoder framework, and borrows the methodology of continuous skip-grams for training. The learned vector representations are evaluated on 13 widely used word similarity benchmarks, and achieved competitive results to that of GloVe. The biggest advantage of the proposed model is its capability of extracting semantic information of audio segments taken directly from raw speech, without relying on any other modalities such as text or images, which are challenging and expensive to collect and annotate.

Yu-An Chung, Shao-Wen Yang, Hsuan-Tien Lin

While deep neural networks have succeeded in several visual applications, such as object recognition, detection, and localization, by reaching very high classification accuracies, it is important to note that many real-world applications demand varying costs for different types of misclassification errors, thus requiring cost-sensitive classification algorithms. Current models of deep neural networks for cost-sensitive classification are restricted to some specific network structures and limited depth. In this paper, we propose a novel framework that can be applied to deep neural networks with any structure to facilitate their learning of meaningful representations for cost-sensitive classification problems. Furthermore, the framework allows end-to-end training of deeper networks directly. The framework is designed by augmenting auxiliary neurons to the output of each hidden layer for layer-wise cost estimation, and including the total estimation loss within the optimization objective. Experimental results on public benchmark visual data sets with two cost information settings demonstrate that the proposed framework outperforms state-of-the-art cost-sensitive deep learning models.

Yu-An Chung, Chao-Chung Wu, Chia-Hao Shen et al.

The vector representations of fixed dimensionality for words (in text) offered by Word2Vec have been shown to be very useful in many application scenarios, in particular due to the semantic information they carry. This paper proposes a parallel version, the Audio Word2Vec. It offers the vector representations of fixed dimensionality for variable-length audio segments. These vector representations are shown to describe the sequential phonetic structures of the audio segments to a good degree, with very attractive real world applications such as query-by-example Spoken Term Detection (STD). In this STD application, the proposed approach significantly outperformed the conventional Dynamic Time Warping (DTW) based approaches at significantly lower computation requirements. We propose unsupervised learning of Audio Word2Vec from audio data without human annotation using Sequence-to-sequence Audoencoder (SA). SA consists of two RNNs equipped with Long Short-Term Memory (LSTM) units: the first RNN (encoder) maps the input audio sequence into a vector representation of fixed dimensionality, and the second RNN (decoder) maps the representation back to the input audio sequence. The two RNNs are jointly trained by minimizing the reconstruction error. Denoising Sequence-to-sequence Autoencoder (DSA) is furthered proposed offering more robust learning.

Yu-An Chung, Hsuan-Tien Lin, Shao-Wen Yang

Deep learning has been one of the most prominent machine learning techniques nowadays, being the state-of-the-art on a broad range of applications where automatic feature extraction is needed. Many such applications also demand varying costs for different types of mis-classification errors, but it is not clear whether or how such cost information can be incorporated into deep learning to improve performance. In this work, we propose a novel cost-aware algorithm that takes into account the cost information into not only the training stage but also the pre-training stage of deep learning. The approach allows deep learning to conduct automatic feature extraction with the cost information effectively. Extensive experimental results demonstrate that the proposed approach outperforms other deep learning models that do not digest the cost information in the pre-training stage.