Bangla-Wave: Improving Bangla Automatic Speech Recognition Utilizing N-gram Language Models

2022-09-13 · Mohammed Rakib, Md. Ismail Hossain, Nabeel Mohammed, Fuad Rahman

Although over 300M around the world speak Bangla, scant work has been done in improving Bangla voice-to-text transcription due to Bangla being a low-resource language. However, with the introduction of the Bengali Common Voice 9.0 speech dataset, Automatic Speech Recognition (ASR) models can now be significantly improved. With 399hrs of speech recordings, Bengali Common Voice is the largest and most diversified open-source Bengali speech corpus in the world. In this paper, we outperform the SOTA pretrained Bengali ASR models by finetuning a pretrained wav2vec2 model on the common voice dataset. We also demonstrate how to significantly improve the performance of an ASR model by adding an n-gram language model as a post-processor. Finally, we do some experiments and hyperparameter tuning to generate a robust Bangla ASR model that is better than the existing ASR models.

📄 PDF Abstract BibTeX arXiv:2209.12650

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling speech-recognition Speech Recognition

BanglaRobustNet: A Hybrid Denoising-Attention Architecture for Robust Bangla Speech Recognition

2026-01-25 · Md Sazzadul Islam Ridoy, Mubaswira Ibnat Zidney, Sumi Akter, Md. Aminur Rahman arxiv

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 Bang…

Speech Recognition

Preparation of Bangla Speech Corpus from Publicly Available Audio \& Text

2020-05-01 · LREC 2020 5 · Shafayat Ahmed, Nafis Sadeq, Sudipta Saha Shubha, Md. Nahidul Islam 외

Automatic speech recognition systems require large annotated speech corpus. The manual annotation of a large corpus is very difficult. In this paper, we focus on the automatic preparation of a speech corpus for Banglades…

Automatic Speech Recognition Automatic Speech Recognition (ASR)speaker-diarization Speaker Diarization+2

Investigating self-supervised, weakly supervised and fully supervised training approaches for multi-domain automatic speech recognition: a study on Bangladeshi Bangla

2022-10-24 · Ahnaf Mozib Samin, M. Humayon Kobir, Md. Mushtaq Shahriyar Rafee, M. Firoz Ahmed 외

Despite huge improvements in automatic speech recognition (ASR) employing neural networks, ASR systems still suffer from a lack of robustness and generalizability issues due to domain shifting. This is mainly because pri…

Automatic Speech Recognition Automatic Speech Recognition (ASR)speech-recognition Speech Recognition+1

Local Feature or Mel Frequency Cepstral Coefficients - Which One is Better for MLN-Based Bangla Speech Recognition?

2013-10-05 · Foyzul Hassan, Mohammed Rokibul Alam Kotwal, Md. Mostafizur Rahman, Mohammad Nasiruddin 외

This paper discusses the dominancy of local features (LFs), as input to the multilayer neural network (MLN), extracted from a Bangla input speech over mel frequency cepstral coefficients (MFCCs). Here, LF-based method co…

Automatic Speech Recognition Automatic Speech Recognition (ASR)speech-recognition Speech Recognition

Pseudo-Labeling for Domain-Agnostic Bangla Automatic Speech Recognition

2023-11-06 · Rabindra Nath Nandi, Mehadi Hasan Menon, Tareq Al Muntasir, Sagor Sarker 외

One of the major challenges for developing automatic speech recognition (ASR) for low-resource languages is the limited access to labeled data with domain-specific variations. In this study, we propose a pseudo-labeling …