Federated Learning (FL) is a novel distributed machine learning which allows thousands of edge devices to train model locally without uploading data concentrically to the server. But since real federated settings are resource-constrained, FL is encountered with systems heterogeneity which causes a lot of stragglers directly and then leads to significantly accuracy reduction indirectly. To solve the problems caused by systems heterogeneity, we introduce a novel self-adaptive federated framework FedSAE which adjusts the training task of devices automatically and selects participants actively to alleviate the performance degradation. In this work, we 1) propose FedSAE which leverages the complete information of devices' historical training tasks to predict the affordable training workloads for each device. In this way, FedSAE can estimate the reliability of each device and self-adaptively adjust the amount of training load per client in each round. 2) combine our framework with Active Learning to self-adaptively select participants. Then the framework accelerates the convergence of the global model. In our framework, the server evaluates devices' value of training based on their training loss. Then the server selects those clients with bigger value for the global model to reduce communication overhead. The experimental result indicates that in a highly heterogeneous system, FedSAE converges faster than FedAvg, the vanilla FL framework. Furthermore, FedSAE outperforms than FedAvg on several federated datasets - FedSAE improves test accuracy by 26.7% and reduces stragglers by 90.3% on average.
This paper introduces Parallel Tacotron 2, a non-autoregressive neural text-to-speech model with a fully differentiable duration model which does not require supervised duration signals. The duration model is based on a novel attention mechanism and an iterative reconstruction loss based on Soft Dynamic Time Warping, this model can learn token-frame alignments as well as token durations automatically. Experimental results show that Parallel Tacotron 2 outperforms baselines in subjective naturalness in several diverse multi speaker evaluations. Its duration control capability is also demonstrated.
We present SpeechStew, a speech recognition model that is trained on a combination of various publicly available speech recognition datasets: AMI, Broadcast News, Common Voice, LibriSpeech, Switchboard/Fisher, Tedlium, and Wall Street Journal. SpeechStew simply mixes all of these datasets together, without any special re-weighting or re-balancing of the datasets. SpeechStew achieves SoTA or near SoTA results across a variety of tasks, without the use of an external language model. Our results include 9.0\% WER on AMI-IHM, 4.7\% WER on Switchboard, 8.3\% WER on CallHome, and 1.3\% on WSJ, which significantly outperforms prior work with strong external language models. We also demonstrate that SpeechStew learns powerful transfer learning representations. We fine-tune SpeechStew on a noisy low resource speech dataset, CHiME-6. We achieve 38.9\% WER without a language model, which compares to 38.6\% WER to a strong HMM baseline with a language model.
We combine recent advancements in end-to-end speech recognition to non-autoregressive automatic speech recognition. We push the limits of non-autoregressive state-of-the-art results for multiple datasets: LibriSpeech, Fisher+Switchboard and Wall Street Journal. Key to our recipe, we leverage CTC on giant Conformer neural network architectures with SpecAugment and wav2vec2 pre-training. We achieve 1.8%/3.6% WER on LibriSpeech test/test-other sets, 5.1%/9.8% WER on Switchboard, and 3.4% on the Wall Street Journal, all without a language model.
Although end-to-end automatic speech recognition (e2e ASR) models are widely deployed in many applications, there have been very few studies to understand models' robustness against adversarial perturbations. In this paper, we explore whether a targeted universal perturbation vector exists for e2e ASR models. Our goal is to find perturbations that can mislead the models to predict the given targeted transcript such as "thank you" or empty string on any input utterance. We study two different attacks, namely additive and prepending perturbations, and their performances on the state-of-the-art LAS, CTC and RNN-T models. We find that LAS is the most vulnerable to perturbations among the three models. RNN-T is more robust against additive perturbations, especially on long utterances. And CTC is robust against both additive and prepending perturbations. To attack RNN-T, we find prepending perturbation is more effective than the additive perturbation, and can mislead the models to predict the same short target on utterances of arbitrary length.
Many mission-critical applications of machine learning (ML) in the real-world require a quality assurance (QA) process before the decisions or predictions of an ML model can be deployed. Because QA4ML users have to view a non-trivial amount of data and perform many input actions to correct errors made by the ML model, an optimally-designed user interface (UI) can reduce the cost of interactions significantly. A UI's effectiveness can be affected by many factors, such as the number of data objects processed concurrently, the types of commands for correcting errors, and the availability of algorithms for assisting users. We propose using simulation to aid the design and optimization of intelligent user interfaces for QA4ML processes. In particular, we focus on simulating the combined effects of human intelligence in selecting appropriate commands and algorithms, and machine intelligence in providing a collection of general-purpose algorithms for reordering data objects to be quality-assured.
This paper introduces PnG BERT, a new encoder model for neural TTS. This model is augmented from the original BERT model, by taking both phoneme and grapheme representations of text as input, as well as the word-level alignment between them. It can be pre-trained on a large text corpus in a self-supervised manner, and fine-tuned in a TTS task. Experimental results show that a neural TTS model using a pre-trained PnG BERT as its encoder yields more natural prosody and more accurate pronunciation than a baseline model using only phoneme input with no pre-training. Subjective side-by-side preference evaluations show that raters have no statistically significant preference between the speech synthesized using a PnG BERT and ground truth recordings from professional speakers.