Related papers: Efficient Weight factorization for Multilingual Sp…

Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting lightweight modules between layers, resulting in the addition of…

In recent years, Long Short-Term Memory (LSTM) has become a popular choice for speech separation and speech enhancement task. The capability of LSTM network can be enhanced by widening and adding more layers. However, this would introduce…

When tasked with supporting multiple languages for a given problem, two approaches have arisen: training a model for each language with the annotation budget divided equally among them, and training on a high-resource language followed by…

Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer…

This paper proposes a technique for adding a new source or target language to an existing multilingual NMT model without re-training it on the initial set of languages. It consists in replacing the shared vocabulary with a small…

We present an analysis tool based on joint matrix factorization for comparing latent representations of multilingual and monolingual models. An alternative to probing, this tool allows us to analyze multiple sets of representations in a…

This paper investigates the impact of word-based RNN language models (RNN-LMs) on the performance of end-to-end automatic speech recognition (ASR). In our prior work, we have proposed a multi-level LM, in which character-based and…

In recent years, language models have become increasingly larger and more complex. However, the input representations for these models continue to rely on simple and greedy subword tokenization methods. In this paper, we propose a novel…

Multilingual Machine Translation promises to improve translation quality between non-English languages. This is advantageous for several reasons, namely lower latency (no need to translate twice), and reduced error cascades (e.g., avoiding…

With the tremendous success of large transformer models in natural language understanding, down-sizing them for cost-effective deployments has become critical. Recent studies have explored the low-rank weight factorization techniques which…

Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and…

This paper proposes a novel, efficient transfer learning method, called Scalable Weight Reparametrization (SWR) that is efficient and effective for multiple downstream tasks. Efficient transfer learning involves utilizing a pre-trained…

Multiple rotation averaging plays a crucial role in computer vision and robotics domains. The conventional optimization-based methods optimize a nonlinear cost function based on certain noise assumptions, while most previous learning-based…

Large language models have recently achieved state of the art performance across a wide variety of natural language tasks. Meanwhile, the size of these models and their latency have significantly increased, which makes their usage costly,…

Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using…

One of the challenges with finetuning pretrained language models (PLMs) is that their tokenizer is optimized for the language(s) it was pretrained on, but brittle when it comes to previously unseen variations in the data. This can for…

Matrix factorization is a key tool in data analysis; its applications include recommender systems, correlation analysis, signal processing, among others. Binary matrices are a particular case which has received significant attention for…

ELMo embeddings (Peters et. al, 2018) had a huge impact on the NLP community and may recent publications use these embeddings to boost the performance for downstream NLP tasks. However, integration of ELMo embeddings in existent NLP…

Large Language Models (LLMs) suffer from huge number of parameters, which restricts their deployment on edge devices. Weight sharing is one promising solution that encourages weight reuse, effectively reducing memory usage with less…

To scale neural speech synthesis to various real-world languages, we present a multilingual end-to-end framework that maps byte inputs to spectrograms, thus allowing arbitrary input scripts. Besides strong results on 40+ languages, the…