Related papers: Transducers with Pronunciation-aware Embeddings fo…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

Cross encoders (CEs) are trained with sentence pairs to detect relatedness. As CEs require sentence pairs at inference, the prevailing view is that they can only be used as re-rankers in information retrieval pipelines. Dual encoders (DEs)…

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Automated audio captioning (AAC) is the task of automatically generating textual descriptions for general audio signals. A captioning system has to identify various information from the input signal and express it with natural language.…

We propose a method for joint multichannel speech dereverberation with two spatial-aware tasks: direction-of-arrival (DOA) estimation and speech separation. The proposed method addresses involved tasks as a sequence to sequence mapping…

In this paper, we propose Stacked DeBERT, short for Stacked Denoising Bidirectional Encoder Representations from Transformers. This novel model improves robustness in incomplete data, when compared to existing systems, by designing a novel…

Tying the weights of the target word embeddings with the target word classifiers of neural machine translation models leads to faster training and often to better translation quality. Given the success of this parameter sharing, we…

Creating meta-embeddings for better performance in language modelling has received attention lately, and methods based on concatenation or merely calculating the arithmetic mean of more than one separately trained embeddings to perform…

Connectionist Temporal Classification (CTC) based end-to-end speech recognition system usually need to incorporate an external language model by using WFST-based decoding in order to achieve promising results. This is more essential to…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice,…

The attention mechanisms are playing a boosting role in advancements in sequence-to-sequence problems. Transformer architecture achieved new state of the art results in machine translation, and it's variants are since being introduced in…

Children speech recognition is indispensable but challenging due to the diversity of children's speech. In this paper, we propose a filter-based discriminative autoencoder for acoustic modeling. To filter out the influence of various…

Automatic pronunciation error detection (APED) plays an important role in the domain of language learning. As for the previous ASR-based APED methods, the decoded results need to be aligned with the target text so that the errors can be…

With the evergrowing sizes of pre-trained models (PTMs), it has been an emerging practice to only provide the inference APIs for users, namely model-as-a-service (MaaS) setting. To adapt PTMs with model parameters frozen, most current…

Neural language models learn word representations, or embeddings, that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural…

Large-scale conversational assistants like Alexa, Siri, Cortana and Google Assistant process every utterance using multiple models for domain, intent and named entity recognition. Given the decoupled nature of model development and large…

Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In addition, translation quality can suffer for low-resource languages. To address this, we introduce…

This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting. Focusing on the encoder-decoder attention mechanism, we prove that attention weights systematically make alignment…

Many speech synthesis datasets, especially those derived from audiobooks, naturally comprise sequences of utterances. Nevertheless, such data are commonly treated as individual, unordered utterances both when training a model and at…