Moreover,weshow that their inductive biases are poorly matched to lifelong learning formulations ofclassification and translation.

Mispronunciation detection and diagnosis (MDD) is a significant part in modern computer aided language learning (CALL) systems. Within MDD, phoneme-level pronunciation assessment is key to helping L2 learners improve their pronunciation. However, most systems are based on a form of goodness of pronunciation (GOP) which requires pre-segmentation of speech into phonetic units. This limits the accuracy of these methods and the possibility to use modern CTC-based acoustic models for their evaluation. In this study, we first propose self-alignment GOP (GOP-SA) that enables the use of CTC-trained ASR models for MDD. Next, we define a more general alignment-free method that takes all possible alignments of the target phoneme into account (GOP-AF). We give a theoretical account of our definition of GOP-AF, an implementation that solves potential numerical issues as well as a proper normalization which makes the method applicable with acoustic models with different peakiness over time. We provide extensive experimental results on the CMU Kids and Speechocean762 datasets comparing the different definitions of our methods, estimating the dependency of GOP-AF on the peakiness of the acoustic models and on the amount of context around the target phoneme. Finally, we compare our methods with recent studies over the Speechocean762 data showing that the feature vectors derived from the proposed method achieve state-of-the-art results on phoneme-level pronunciation assessment.

Neural finite-state transducers (NFSTs) form an expressive family of neurosymbolic sequence transduction models. An NFST models each string pair as having been generated by a latent path in a finite-state transducer. As they are deep generative models, both training and inference of NFSTs require inference networks that approximate posterior distributions over such latent variables. In this paper, we focus on the resulting challenge of imputing the latent alignment path that explains a given pair of input and output strings (e.g., during training). We train three autoregressive approximate models for amortized inference of the path, which can then be used as proposal distributions for importance sampling. All three models perform lookahead. Our most sophisticated (and novel) model leverages the FST structure to consider the graph of future paths; unfortunately, we find that it loses out to the simpler approaches -- except on an artificial task that we concocted to confuse the simpler approaches.

Despite rapid progress, current deep learning methods face a number of critical challenges. These include high energy consumption, catastrophic forgetting, dependance on global losses, and an inability to reason symbolically. By combining concepts from information bottleneck theory and vector-symbolic architectures, we propose and implement a novel information processing architecture, the 'Bridge network.' We show this architecture provides unique advantages which can address the problem of global losses and catastrophic forgetting. Furthermore, we argue that it provides a further basis for increasing energy efficiency of execution and the ability to reason symbolically.

Features of range asymmetric number system encoding and decoding Abstract Innovations in range asymmetric number system ("RANS") coding and decoding are described herein. Some of the innovations relate to hardware implementations of RANS decoding that organize operations in two phases, which can improve the computational efficiency of RANS decoding. Other innovations relate to adapting RANS encoding/decoding for different distributions or patterns of values for symbols. For example, RANS encoding/decoding can adapt by switching a default symbol width (the number of bits per symbol), adjusting symbol width on a fragment-by-fragment basis for different fragments of symbols, switching between different static probability models on a fragment-by-fragment basis for different fragments of symbols, and/or selectively flushing (or retaining) the state of a RANS decoder on a fragment-by-fragment basis for different fragments of symbols. In many cases, such innovations can improve compression efficiency while also providing computationally efficient performance.

People can learn a new concept and use it compositionally, understanding how to "blicket twice" after learning how to "blicket." In contrast, powerful sequence-to-sequence (seq2seq) neural networks fail such tests of compositionality, especially when composing new concepts together with existing concepts. In this paper, I show that neural networks can be trained to generalize compositionally through meta seq2seq learning. In this approach, models train on a series of seq2seq problems to acquire the compositional skills needed to solve new seq2seq problems. Meta se2seq learning solves several of the SCAN tests for compositional learning and can learn to apply rules to variables.

Dzmitry Bahdanau Jacobs University Bremen, Germany Yoshua Bengio Université de Montréal CIFAR Senior Fellow We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bidirectional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of phonemes. The alignment between the input and output sequences is established using an attention mechanism: the decoder emits each symbol based on a context created with a subset of input symbols selected by the attention mechanism. We report initial results demonstrating that this new approach achieves phoneme error rates that are comparable to the state-of-the-art HMM-based decoders, on the TIMIT dataset.

We extend a recent synchronization analysis of exact finite-state sources to nonexact sources for which synchronization occurs only asymptotically. Although the proof methods are quite different, the primary results remain the same. We find that an observer's average uncertainty in the source state vanishes exponentially fast and, as a consequence, an observer's average uncertainty in predicting future output converges exponentially fast to the source entropy rate.

We investigate a family of inference problems on Markov models, where many sample paths are drawn from a Markov chain and partial information is revealed to an observer who attempts to reconstruct the sample paths. We present algorithms and hardness results for several variants of this problem which arise by revealing different information to the observer and imposing different requirements for the reconstruction of sample paths. Our algorithms are analogous to the classical Viterbi algorithm for Hidden Markov Models, which finds the single most probable sample path given a sequence of observations. Our work is motivated by an important application in ecology: inferring bird migration paths from a large database of observations.