Related papers: Adaptive Multi-Corpora Language Model Training for…

This paper presents a novel training method, Conditional Masked Language Modeling (CMLM), to effectively learn sentence representations on large scale unlabeled corpora. CMLM integrates sentence representation learning into MLM training by…

Deep learning-based speech enhancement methods have significantly improved speech quality and intelligibility. Convolutional neural networks (CNNs) have been proven to be essential components of many high-performance models. In this paper,…

Domain Adaptation (DA) of Neural Machine Translation (NMT) model often relies on a pre-trained general NMT model which is adapted to the new domain on a sample of in-domain parallel data. Without parallel data, there is no way to estimate…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…

Ordering the selection of training data using active learning can lead to improvements in learning efficiently from smaller corpora. We present an exploration of active learning approaches applied to three grounded language problems of…

With the rapid development of natural language processing technology, large-scale language models (LLM) have achieved remarkable results in a variety of tasks. However, how to effectively train these huge models and improve their…

Natural Language Processing (NLP) and Voice Recognition agents are rapidly evolving healthcare by enabling efficient, accessible, and professional patient support while automating grunt work. This report serves as my self project wherein…

This paper introduces a new data augmentation method for neural machine translation that can enforce stronger semantic consistency both within and across languages. Our method is based on Conditional Masked Language Model (CMLM) which is…

Source separation can improve automatic speech recognition (ASR) under multi-party meeting scenarios by extracting single-speaker signals from overlapped speech. Despite the success of self-supervised learning models in single-channel…

This paper introduces the integration of language-specific bi-directional context into a speech large language model (SLLM) to improve multilingual continuous conversational automatic speech recognition (ASR). We propose a character-level…

Recently, Large language models (LLMs) with in-context learning have demonstrated remarkable potential in handling neural machine translation. However, existing evidence shows that LLMs are prompt-sensitive and it is sub-optimal to apply…

This paper describes our Triple X speech recognition system submitted to Task 1 of the Multi-Lingual Conversational Speech Language Modeling (MLC-SLM) Challenge. Our work focuses on optimizing speech recognition accuracy in multilingual…

We present Dynamic Skill Adaptation (DSA), an adaptive and dynamic framework to adapt novel and complex skills to Large Language Models (LLMs). Compared with previous work which learns from human-curated and static data in random orders, we…

Automatic Speech Recognition (ASR) systems have found their use in numerous industrial applications in very diverse domains creating a need to adapt to new domains with small memory and deployment overhead. In this work, we introduce…

Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…

Modeling the errors of a speech recognizer can help simulate errorful recognized speech data from plain text, which has proven useful for tasks like discriminative language modeling, improving robustness of NLP systems, where limited or…

Integrating audio encoders with LLMs through connectors has enabled these models to process and comprehend audio modalities, significantly enhancing speech-to-text tasks, including automatic speech recognition (ASR) and automatic speech…

Local dialects influence people to pronounce words of the same language differently from each other. The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic…

In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker…

For several purposes in Natural Language Processing (NLP), such as Information Extraction, Sentiment Analysis or Chatbot, Named Entity Recognition (NER) holds an important role as it helps to determine and categorize entities in text into…