Efficient sequence transduction by jointly predicting tokens and durations
This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for
sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by …
sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by …
End-to-end speech recognition contextualization with large language models
In recent years, Large Language Models (LLMs) have garnered significant attention from the
research community due to their exceptional performance and generalization capabilities. In …
research community due to their exceptional performance and generalization capabilities. In …
Token-level serialized output training for joint streaming asr and st leveraging textual alignments
In real-world applications, users often require both translations and transcriptions of speech
to enhance their comprehension, particularly in streaming scenarios where incremental …
to enhance their comprehension, particularly in streaming scenarios where incremental …
Contextual biasing of named-entities with large language models
We explore contextual biasing with Large Language Models (LLMs) to enhance Automatic
Speech Recognition (ASR) in second-pass rescoring. Our approach introduces the …
Speech Recognition (ASR) in second-pass rescoring. Our approach introduces the …
Improving large-scale deep biasing with phoneme features and text-only data in streaming transducer
Deep biasing for the Transducer can improve the recognition performance of rare words or
contextual entities, which is essential in practical applications, especially for streaming …
contextual entities, which is essential in practical applications, especially for streaming …
Spike-Triggered Contextual Biasing for End-to-End Mandarin Speech Recognition
The attention-based deep contextual biasing method has been demonstrated to effectively
improve the recognition performance of end-to-end automatic speech recognition (ASR) …
improve the recognition performance of end-to-end automatic speech recognition (ASR) …
Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU
The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on
decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle …
decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle …
Key Frame Mechanism For Efficient Conformer Based End-to-end Speech Recognition
Recently, Conformer as a backbone network for end-to-end automatic speech recognition
achieved state-of-the-art performance. The Conformer block leverages a self-attention …
achieved state-of-the-art performance. The Conformer block leverages a self-attention …
Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss
Contextualized end-to-end automatic speech recognition has been an active research area,
with recent efforts focusing on the implicit learning of contextual phrases based on the final …
with recent efforts focusing on the implicit learning of contextual phrases based on the final …
Improving ASR Contextual Biasing with Guided Attention
In this paper, we propose a Guided Attention (GA) auxiliary training loss, which improves the
effectiveness and robustness of automatic speech recognition (ASR) contextual biasing …
effectiveness and robustness of automatic speech recognition (ASR) contextual biasing …