Related papers: Restoring Rhythm: Punctuation Restoration Using Tr…

Training models for Natural Language Processing (NLP) requires substantial computational resources and time, posing significant challenges, especially for NLP development in Bangla, where access to high-end hardware is often limited. In…

Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet its utility in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including…

Lemmatization holds significance in both natural language processing (NLP) and linguistics, as it effectively decreases data density and aids in comprehending contextual meaning. However, due to the highly inflected nature and morphological…

Neural Language Models (NLM), when trained and evaluated with context spanning multiple utterances, have been shown to consistently outperform both conventional n-gram language models and NLMs that use limited context. In this paper, we…

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…

Presented here is a method for automatic punctuation restoration in Swedish using a BERT model. The method is based on KB-BERT, a publicly available, neural network language model pre-trained on a Swedish corpus by National Library of…

This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on short segments containing only lowercase or partial…

Punctuation prediction for automatic speech recognition (ASR) output transcripts plays a crucial role for improving the readability of the ASR transcripts and for improving the performance of downstream natural language processing…

Batch normalization (BN) is an effective method to accelerate model training and improve the generalization performance of neural networks. In this paper, we propose an improved batch normalization technique called attentive batch…

In this study, we investigate the integration of a large language model (LLM) with an automatic speech recognition (ASR) system, specifically focusing on enhancing rare word recognition performance. Using a 190,000-hour dataset primarily…

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train…

The applications of recurrent neural networks in machine translation are increasing in natural language processing. Besides other languages, Bangla language contains a large amount of vocabulary. Improvement of English to Bangla machine…

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance…

Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR architectures connect a speech encoder to a large language model via a projection module,…

Bangla, one of the most widely spoken languages, remains underrepresented in state-of-the-art automatic speech recognition (ASR) research, particularly under noisy and speaker-diverse conditions. This paper presents BanglaRobustNet, a…

Sentence-level embedding is essential for various tasks that require understanding natural language. Many studies have explored such embeddings for high-resource languages like English. However, low-resource languages like Bengali (a…

This paper proposes a novel label-synchronous speech-to-text alignment technique for automatic speech recognition (ASR). The speech-to-text alignment is a problem of splitting long audio recordings with un-aligned transcripts into…

Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this…

Punctuation plays a vital role in structuring meaning, yet current models often struggle to restore it accurately in transcripts of spontaneous speech, especially in the presence of disfluencies such as false starts and backtracking. These…

Bangla Sign Language (BdSL) translation represents a low-resource NLP task due to the lack of large-scale datasets that address sentence-level translation. Correspondingly, existing research in this field has been limited to word and…