8 citations · 20 across the 8 of their papers we have counts for
9 papers
External Language Model Integration for Factorized Neural Transducers
Michael Levit, Sarangarajan Parthasarathy, Cem Aksoylar +2
We propose an adaptation method for factorized neural transducers (FNT) with external language models. We demonstrate that both neural and n-gram external LMs add significantly mor…
Multilingual Transformer Language Model for Speech Recognition in Low-resource Languages
Li Miao, Jian Wu, Piyush Behre +2
It is challenging to train and deploy Transformer LMs for hybrid speech recognition 2nd pass re-ranking in low-resource languages due to (1) data scarcity in low-resource languages…
Factorized Neural Transducer for Efficient Language Model Adaptation
Xie Chen, Zhong Meng, Sarangarajan Parthasarathy +1
In recent years, end-to-end (E2E) based automatic speech recognition (ASR) systems have achieved great success due to their simplicity and promising performance. Neural Transducer…
Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition
Zhong Meng, Naoyuki Kanda, Yashesh Gaur +6
The efficacy of external language model (LM) integration with existing end-to-end (E2E) automatic speech recognition (ASR) systems can be improved significantly using the internal…
Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition
Zhong Meng, Sarangarajan Parthasarathy, Eric Sun +7
The external language models (LM) integration remains a challenging task for end-to-end (E2E) automatic speech recognition (ASR) which has no clear division between acoustic and la…
LSTM-LM with Long-Term History for First-Pass Decoding in Conversational Speech Recognition
Xie Chen, Sarangarajan Parthasarathy, William Gale +2
LSTM language models (LSTM-LMs) have been proven to be powerful and yielded significant performance improvements over count based n-gram LMs in modern speech recognition systems. D…
Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability
Jinyu Li, Rui Zhao, Zhong Meng +8
Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic spee…
Long-span language modeling for speech recognition
Sarangarajan Parthasarathy, William Gale, Xie Chen +2
We explore neural language modeling for speech recognition where the context spans multiple sentences. Rather than encode history beyond the current sentence using a cache of words…
Entity-Aware Language Model as an Unsupervised Reranker
Mohammad Sadegh Rasooli, Sarangarajan Parthasarathy
In language modeling, it is difficult to incorporate entity relationships from a knowledge-base. One solution is to use a reranker trained with global features, in which global fea…