Implementing contextual biasing in GPU decoder for online ASR
GPU decoding significantly accelerates the output of ASR predictions. While GPUs are already being used for online ASR decoding, post-processing and rescoring on GPUs have not been properly investigated yet. Rescoring with available contextual information can considerably improve ASR predictions. Previous studies have proven the viability of lattice rescoring in decoding and biasing language model (LM) weights in offline and online CPU scenarios. In real-time GPU decoding, partial recognition hypotheses are produced without lattice generation, which makes the implementation of biasing more complex. The paper proposes and describes an approach to integrate contextual biasing in real-time GPU decoding while exploiting the standard Kaldi GPU decoder. Besides the biasing of partial ASR predictions, our approach also permits dynamic context switching allowing a flexible rescoring per each speech segment directly on GPU. The code is publicly released and tested with open-sourced test sets.
Code (1)
Tasks
CPUDecoderGPULanguage ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
A Neural Model for Contextual Biasing Score Learning and Filtering
Contextual biasing improves automatic speech recognition (ASR) by integrating external knowledge, such as user-specific phrases or entities, during decoding. In this work, we use an attention-based biasing decoder to pro…
Speech RecognitionEfficient Long-Form Speech Recognition for General Speech In-Context Learning
We propose a novel approach to end-to-end automatic speech recognition (ASR) to achieve efficient speech in-context learning (SICL) for (i) long-form speech decoding, (ii) test-time speaker adaptation, and (iii) test-tim…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderForm+3Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition
Contextual knowledge is important for real-world automatic speech recognition (ASR) applications. In this paper, a novel tree-constrained pointer generator (TCPGen) component is proposed that incorporates such knowledge …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognition+1CIF-based Collaborative Decoding for End-to-end Contextual Speech Recognition
End-to-end (E2E) models have achieved promising results on multiple speech recognition benchmarks, and shown the potential to become the mainstream. However, the unified structure and the E2E training hamper injecting co…
Decoderspeech-recognitionSpeech RecognitionTurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree
Recognizing specific key phrases is an essential task for contextualized Automatic Speech Recognition (ASR). However, most existing context-biasing approaches have limitations associated with the necessity of additional …
Speech Recognition