-
SLT 20222022End-to-end speech recognition models trained using joint Connectionist Temporal Classification (CTC)-Attention loss have gained popularity recently. In these models, a non-autoregressive CTC decoder is often used at inference time due to its speed and simplicity. However, such models are hard to personalize because of their conditional independence assumption that prevents output tokens from previous time
-
SLT 20222022For on-device automatic speech recognition (ASR), quantization aware training (QAT) is ubiquitous to achieve the trade-off between model predictive performance and efficiency. Among existing QAT methods, one major drawback is that the quantization centroids have to be predetermined and fixed. To overcome this limitation, we introduce a regularization-free, “soft-to-hard” compression mechanism with self-adjustable
-
AACL 20222022Pre-trained language models (LMs) obtain state-of-the-art performance when adapted to text classification tasks. However, when using such models in real-world applications, efficiency considerations are paramount. In this paper, we study how different training procedures that adapt LMs to text classification perform, as we vary model and train set size. More specifically, we compare standard fine-tuning
-
AACL 20222022Task-oriented dialog systems deployed in real-world applications are often challenged by out-of-distribution queries. These systems should not only reliably detect utterances with unsupported intents (semantic shift), but also generalize to covariate shift (supported intents from unseen distributions). However, none of the existing benchmarks for open-world intent classification focus on the second aspect
-
AACL-IJCNLP 20222022Reasoning with preconditions such as “glass can be used for drinking water unless the glass is shattered” remains an open problem for language models. The main challenge lies in the scarcity of preconditions data and model’s lack of support for such reasoning. We present PInKS , Preconditioned Commonsense Inference with WeaK Supervision, an improved model for reasoning with preconditions through minimum
Related content
-
September 28, 2021Preference teaching for Alexa, Alexa Custom Sound Event Detection, and Ring Custom Event Alerts let customers configure machine learning models.
-
September 23, 2021Droppo discusses his work in the field of speech recognition and signal processing.
-
September 23, 2021The Amazon-sponsored FEVEROUS dataset and shared task challenge researchers to create more advanced fact-checking systems.
-
September 21, 2021Dataset contains more than 11,000 newly collected dialogues to aid research in open-domain conversation.
-
September 13, 2021How Amazon intern Michael Saxon uses his experience with automatic speech recognition models to help Alexa answer complex queries.
-
September 10, 2021Data augmentation makes examples more realistic, while continual-learning techniques prevent “catastrophic forgetting”.