Related papers: Model Interpolation with Trans-dimensional Random …
Recurrent neural networks (RNNs), especially long short-term memory (LSTM) RNNs, are effective network for sequential task like speech recognition. Deeper LSTM models perform well on large vocabulary continuous speech recognition, because…
Recognition of Hungarian conversational telephone speech is challenging due to the informal style and morphological richness of the language. Recurrent Neural Network Language Model (RNNLM) can provide remedy for the high perplexity of the…
In recent studies, linear recurrent neural networks (LRNNs) have achieved Transformer-level performance in natural language and long-range modeling, while offering rapid parallel training and constant inference cost. With the resurgence of…
There has been considerable interest in using surprisal from Transformer-based language models (LMs) as predictors of human sentence processing difficulty. Recent work has observed an inverse scaling relationship between Transformers'…
We develop a representation suitable for the unconstrained recognition of words in natural images: the general case of no fixed lexicon and unknown length. To this end we propose a convolutional neural network (CNN) based architecture which…
Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability. However, it is challenging to adapt it with text-only data. Factorized neural transducer (FNT) model was proposed to…
We introduce $k$NN-LMs, which extend a pre-trained neural language model (LM) by linearly interpolating it with a $k$-nearest neighbors ($k$NN) model. The nearest neighbors are computed according to distance in the pre-trained LM embedding…
Automatic speech recognition (ASR) systems have achieved strong performance on general transcription tasks. However, they continue to struggle with recognizing rare named entities and adapting to domain mismatches. In contrast, large…
This paper presents an empirical study of two widely-used sequence prediction models, Conditional Random Fields (CRFs) and Long Short-Term Memory Networks (LSTMs), on two fundamental tasks for Vietnamese text processing, including…
Recurrent neural network grammars (RNNG) are generative models of language which jointly model syntax and surface structure by incrementally generating a syntax tree and sentence in a top-down, left-to-right order. Supervised RNNGs achieve…
We introduce a novel discriminative word alignment model, which we integrate into a Transformer-based machine translation model. In experiments based on a small number of labeled examples (~1.7K-5K sentences) we evaluate its performance…
We consider phrase based Language Models (LM), which generalize the commonly used word level models. Similar concept on phrase based LMs appears in speech recognition, which is rather specialized and thus less suitable for machine…
Neural language models (LMs) are typically trained using only lexical features, such as surface forms of words. In this paper, we argue this deprives the LM of crucial syntactic signals that can be detected at high confidence using existing…
Turn-taking is a fundamental mechanism in human communication that ensures smooth and coherent verbal interactions. Recent advances in Large Language Models (LLMs) have motivated their use in improving the turn-taking capabilities of Spoken…
Large Language Models (LLMs) have recently revolutionized the NLP field, while they still fall short in some specific down-stream tasks. In the work, we focus on utilizing LLMs to perform machine translation, where we observe that two…
Chinese input recommendation plays an important role in alleviating human cost in typing Chinese words, especially in the scenario of mobile applications. The fundamental problem is to predict the conditional probability of the next word…
Speech model adaptation is crucial to handle the discrepancy between server-side proxy training data and actual data received on local devices of users. With the use of federated learning (FL), we introduce an efficient approach on…
Modeling unit and model architecture are two key factors of Recurrent Neural Network Transducer (RNN-T) in end-to-end speech recognition. To improve the performance of RNN-T for Mandarin speech recognition task, a novel transformer…
Segmental conditional random fields (SCRFs) and connectionist temporal classification (CTC) are two sequence labeling methods used for end-to-end training of speech recognition models. Both models define a transcription probability by…
Neural language models (NLM) have been shown to outperform conventional n-gram language models by a substantial margin in Automatic Speech Recognition (ASR) and other tasks. There are, however, a number of challenges that need to be…