Related papers: Applying wav2vec2 for Speech Recognition on Bengal…
Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production…
Wav2Vec2.0 is a state-of-the-art model which learns speech representations through unlabeled speech data, aka, self supervised learning. The pretrained model is then fine tuned on small amounts of labeled data to use it for speech-to-text…
Automatic speech recognition (ASR) converts the human voice into readily understandable and categorized text or words. Although Bengali is one of the most widely spoken languages in the world, there have been very few studies on Bengali…
Automatic detection and severity level classification of dysarthria directly from acoustic speech signals can be used as a tool in medical diagnosis. In this work, the pre-trained wav2vec 2.0 model is studied as a feature extractor to build…
In recent years, the standard hybrid DNN-HMM speech recognizers are outperformed by the end-to-end speech recognition systems. One of the very promising approaches is the grapheme Wav2Vec 2.0 model, which uses the self-supervised…
Recent advances in self-supervised learning through contrastive training have shown that it is possible to learn a competitive speech recognition system with as little as 10 minutes of labeled data. However, these systems are…
Wav2vec2.0 is a popular self-supervised pre-training framework for learning speech representations in the context of automatic speech recognition (ASR). It was shown that wav2vec2.0 has a good robustness against the domain shift, while the…
Self-training and unsupervised pre-training have emerged as effective approaches to improve speech recognition systems using unlabeled data. However, it is not clear whether they learn similar patterns or if they can be effectively…
Recently, there have been tremendous research outcomes in the fields of speech recognition and natural language processing. This is due to the well-developed multi-layers deep learning paradigms such as wav2vec2.0, Wav2vecU, WavBERT, and…
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…
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…
This paper explores the use of Dutch archival television broadcast data for self-supervised learning of speech foundation models, specifically wav2vec 2.0. We first study data quality assumptions for pre-training, and show how music, noise…
Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning. It follows a two-stage training process of pre-training and fine-tuning, and performs well in speech recognition tasks especially ultra-low…
Recent advances in neural text-to-speech research have been dominated by two-stage pipelines utilizing low-level intermediate speech representation such as mel-spectrograms. However, such predetermined features are fundamentally limited,…
Speech Emotion Recognition (SER) is a challenging task due to limited data and blurred boundaries of certain emotions. In this paper, we present a comprehensive approach to improve the SER performance throughout the model lifecycle,…
Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired…
This work considers training neural networks for speaker recognition with a much smaller dataset size compared to contemporary work. We artificially restrict the amount of data by proposing three subsets of the popular VoxCeleb2 dataset.…
While Word2Vec represents words (in text) as vectors carrying semantic information, audio Word2Vec was shown to be able to represent signal segments of spoken words as vectors carrying phonetic structure information. Audio Word2Vec can be…
In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech…
Neural latent variable models enable the discovery of interesting structure in speech audio data. This paper presents a comparison of two different approaches which are broadly based on predicting future time-steps or auto-encoding the…