Related papers: A systematic comparison of grapheme-based vs. phon…
End-To-End speech recognition have become increasingly popular in mandarin speech recognition and achieved delightful performance. Mandarin is a tonal language which is different from English and requires special treatment for the acoustic…
End-to-end (E2E) automatic speech recognition (ASR) systems have revolutionized the field by integrating all components into a single neural network, with attention-based encoder-decoder models achieving state-of-the-art performance.…
Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing…
Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection…
Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…
Encoder-decoder models have become an effective approach for sequence learning tasks like machine translation, image captioning and speech recognition, but have yet to show competitive results for handwritten text recognition. To this end,…
Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/ HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters…
Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context…
Speech models have gained traction thanks to increase in accuracy from novel transformer architectures. While this impressive increase in performance across automatic speech recognition (ASR) benchmarks is noteworthy, there is still much…
Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs…
Speech Recognition (ASR) due to phoneme distortions and high variability. While self-supervised ASR models like Wav2Vec, HuBERT, and Whisper have shown promise, their effectiveness in dysarthric speech remains unclear. This study…
Recent research has shown that attention-based sequence-to-sequence models such as Listen, Attend, and Spell (LAS) yield comparable results to state-of-the-art ASR systems on various tasks. In this paper, we describe the development of such…
Since Bahdanau et al. [1] first introduced attention for neural machine translation, most sequence-to-sequence models made use of attention mechanisms [2, 3, 4]. While they produce soft-alignment matrices that could be interpreted as…
The success of self-attention in NLP has led to recent applications in end-to-end encoder-decoder architectures for speech recognition. Separately, connectionist temporal classification (CTC) has matured as an alignment-free,…
We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language models (LMs) to facilitate the extraction of linguistic information. The proposed models, BERT-CTC and BECTRA, are…
Recently, pre-trained models with phonetic supervision have demonstrated their advantages for crosslingual speech recognition in data efficiency and information sharing across languages. However, a limitation is that a pronunciation lexicon…
Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining…
We describe here our work with automatic speech recognition (ASR) in the context of voice search functionality on the Flipkart e-Commerce platform. Starting with the deep learning architecture of Listen-Attend-Spell (LAS), we build upon and…
Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle this issue is to…
Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement of the vulnerabilities present in the ASR model bear…