477 citations · 1.1k across the 39 of their papers we have counts for
11 papers · 1 filter
End-to-End Speech Recognition Contextualization with Large Language Models
Egor Lakomkin, Chunyang Wu, Yassir Fathullah +3
In recent years, Large Language Models (LLMs) have garnered significant attention from the research community due to their exceptional performance and generalization capabilities.…
Prompting Large Language Models with Speech Recognition Abilities
Yassir Fathullah, Chunyang Wu, Egor Lakomkin +9
Large language models have proven themselves highly flexible, able to solve a wide range of generative tasks, such as abstractive summarization and open-ended question answering. I…
Multi-Head State Space Model for Speech Recognition
Yassir Fathullah, Chunyang Wu, Yuan Shangguan +8
State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches. I…
Improving Fast-slow Encoder based Transducer with Streaming Deliberation
Ke Li, Jay Mahadeokar, Jinxi Guo +5
This paper introduces a fast-slow encoder based transducer with streaming deliberation for end-to-end automatic speech recognition. We aim to improve the recognition accuracy of th…
Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers
Duc Le, Frank Seide, Yuhao Wang +4
We show how factoring the RNN-T's output distribution can significantly reduce the computation cost and power consumption for on-device ASR inference with no loss in accuracy. With…
Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution
Yangyang Shi, Chunyang Wu, Dilin Wang +9
This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution. Many works apply the causal convolution to improve streaming transf…
On lattice-free boosted MMI training of HMM and CTC-based full-context ASR models
Xiaohui Zhang, Vimal Manohar, David Zhang +7
Hybrid automatic speech recognition (ASR) models are typically sequentially trained with CTC or LF-MMI criteria. However, they have vastly different legacies and are usually implem…
Weak-Attention Suppression For Transformer Based Speech Recognition
Yangyang Shi, Yongqiang Wang, Chunyang Wu +5
Transformers, originally proposed for natural language processing (NLP) tasks, have recently achieved great success in automatic speech recognition (ASR). However, adjacent acousti…
Transformer-Transducer: End-to-End Speech Recognition with Self-Attention
Ching-Feng Yeh, Jay Mahadeokar, Kaustubh Kalgaonkar +6
We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with…
From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition
Duc Le, Xiaohui Zhang, Weiyi Zheng +3
There is an implicit assumption that traditional hybrid approaches for automatic speech recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to g…
G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR
Duc Le, Thilo Koehler, Christian Fuegen +1
Grapheme-based acoustic modeling has recently been shown to outperform phoneme-based approaches in both hybrid and end-to-end automatic speech recognition (ASR), even on non-phonem…