paper-with-me

홈 › Papers

Byte Pair Encoding Is All You Need For Automatic Bengali Speech Recognition

2024-01-28 · Ahnaf Mozib Samin

Byte pair encoding (BPE) emerges as an effective tokenization method for tackling the out-of-vocabulary (OOV) challenge in various natural language and speech processing tasks. Recent research highlights the dependency of BPE subword tokenization's efficacy on the morphological nature of the language, particularly in languages rich in inflectional morphology, where fewer BPE merges suffice for generating highly productive tokens. Motivated by this, our study empirically identifies the optimal number of BPE tokens for Bengali, a language known for its morphological complexity, thus enhancing out-of-distribution automatic speech recognition (ASR) performance. Experimental evaluation reveals that an excessively high number of BPE tokens can lead to overfitting, while approximately 500-1000 tokens result in superior OOV performance. Furthermore, we conduct a comparative analysis of BPE with character-based and unigram-based tokenization methods. By introducing BPE tokenization to Bengali ASR, we achieve a substantial reduction in the word error rate (WER) from 66.44% in our character-based baseline system to 63.80% on the LB-ASRTD eval set and from 46.34% to 42.80% on the SHRUTI eval set, both of which include out-of-distribution data.

📄 PDF Abstract BibTeX arXiv:2401.15532

Code (0)

등록된 구현이 없습니다.

Tasks

AllAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Meaningless yet meaningful: Morphology grounded subword-level NMT

2018-06-01 · WS 2018 6 · Tamali Banerjee, Pushpak Bhattacharyya

We explore the use of two independent subsystems Byte Pair Encoding (BPE) and Morfessor as basic units for subword-level neural machine translation (NMT). We show that, for linguistically distant language-pairs Morfessor…

Machine TranslationNMTSegmentationTranslation+1

Evaluating Subword Tokenization Techniques for Bengali: A Benchmark Study with BengaliBPE

2025-11-07 · Firoj Ahmmed Patwary, Abdullah Al Noman arxiv

Tokenization is an important first step in Natural Language Processing (NLP) pipelines because it decides how models learn and represent linguistic information. However, current subword tokenizers like SentencePiece or H…

News Classification

Bilingual End-to-End ASR with Byte-Level Subwords

2022-05-01 · Liuhui Deng, Roger Hsiao, Arnab Ghoshal

In this paper, we investigate how the output representation of an end-to-end neural network affects multilingual automatic speech recognition (ASR). We study different representations including character-level, byte-leve…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Code Completion using Neural Attention and Byte Pair Encoding

2020-04-14 · Youri Arkesteijn, Nikhil Saldanha, Bastijn Kostense

In this paper, we aim to do code completion based on implementing a Neural Network from Li et. al.. Our contribution is that we use an encoding that is in-between character and word encoding called Byte Pair Encoding (BP…

Code Completion

Improving Natural Language Understanding by Reverse Mapping Bytepair Encoding

2019-11-01 · CONLL 2019 11 · Chaodong Tong, Huailiang Peng, Qiong Dai, Lei Jiang 외

We propose a method called reverse mapping bytepair encoding, which maps named-entity information and other word-level linguistic features back to subwords during the encoding procedure of bytepair encoding (BPE). We emp…

Natural Language UnderstandingRTESST-2