A study on the challenges and opportunities of speech recognition for Bengali language

Mridha, M. F.; Ohi, Abu Quwsar; Hamid, Abd.; Monowar, Muhammad Mostafa

doi:10.1007/s10462-021-10083-3

Cited by 14 publications

(3 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These recurrent layers produce a final output by identifying patterns based on both previous and current input data. The network is trained to use backpropagation in conjunction with the CTC (Connectionist Temporal Classification) loss function [16]. Broadly speaking, three primary TL methods have been used in the context of AMs [5]: feature normalization, discriminative training, and subspace-based TL.…”

Section: Tl Of Acoustic Model (Am)mentioning

confidence: 99%

Customization of the ASR System for ATC Speech with Improved Fusion

Fan,

Pan

2024

Aerospace

View full text Add to dashboard Cite

In recent years, automatic speech recognition (ASR) technology has improved significantly. However, the training process for an ASR model is complex, involving large amounts of data and a large number of algorithms. The task of training a new model for air traffic control (ATC) is considerable, as it may require many researchers for its maintenance and upgrading. In this paper, we developed an improved fusion method that can adapt the language model (LM) in ASR to the domain of air traffic control. Instead of using vocabulary in traditional fusion, this method uses the ATC instructions to improve the LM. The perplexity shows that the LM of the improved fusion is much better than that of the use of vocabulary. With vocabulary fusion, the CER in the ATC corpus decreases from 0.3493 to 0.2876. The improved fusion reduces the CER of the ATC corpora from 0.3493 to 0.2761. Although there is only a difference of less than 2% between the two fusions, the perplexity shows that the LM of the improved fusion is much better.

show abstract

Section: Tl Of Acoustic Model (Am)mentioning

confidence: 99%

Customization of the ASR System for ATC Speech with Improved Fusion

Fan,

Pan

2024

Aerospace

View full text Add to dashboard Cite

show abstract

“…The recurrent layers create a final output by looking for patterns based on prior and current input information. Backpropagation is used to train the network with the CTC loss [94]. Generally, three main DTL strategies have been used with AMs:…”

Section: Dtl For Acoustic Models (Ams)mentioning

confidence: 99%

“…For example, the architecture portrayed in Fig. 9, aims to build a seq2seq model [94]. The seq2seq's encoder network consists of a stack of RNNs that create embedding vectors.…”

Section: Dtl-based Sequence-to-sequence Modelmentioning

confidence: 99%

Video surveillance using deep transfer learning and deep domain adaptation: Towards better generalization

Himeur

Al‐Maadeed

Kheddar

et al. 2023

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Domain Generalization with Small Data

Chen,

Gal,

Yan

et al. 2024

Int J Comput Vis

View full text Add to dashboard Cite

In this work, we propose to tackle the problem of domain generalization in the context of insufficient samples. Instead of extracting latent feature embeddings based on deterministic models, we propose to learn a domain-invariant representation based on the probabilistic framework by mapping each data point into probabilistic embeddings. Specifically, we first extend empirical maximum mean discrepancy (MMD) to a novel probabilistic MMD that can measure the discrepancy between mixture distributions (i.e., source domains) consisting of a series of latent distributions rather than latent points. Moreover, instead of imposing the contrastive semantic alignment (CSA) loss based on pairs of latent points, a novel probabilistic CSA loss encourages positive probabilistic embedding pairs to be closer while pulling other negative ones apart. Benefiting from the learned representation captured by probabilistic models, our proposed method can marriage the measurement on the distribution over distributions (i.e., the global perspective alignment) and the distribution-based contrastive semantic alignment (i.e., the local perspective alignment). Extensive experimental results on three challenging medical datasets show the effectiveness of our proposed method in the context of insufficient data compared with state-of-the-art methods.

show abstract

A study on the challenges and opportunities of speech recognition for Bengali language

Cited by 14 publications

References 54 publications

Customization of the ASR System for ATC Speech with Improved Fusion

Customization of the ASR System for ATC Speech with Improved Fusion

Video surveillance using deep transfer learning and deep domain adaptation: Towards better generalization

Domain Generalization with Small Data

Contact Info

Product

Resources

About