Class LM and Word Mapping for Contextual Biasing in End-to-End ASR

Huang, Rongqing; Abdel-Hamid, Ossama; Li, Xinwei; Evermann, G.

doi:10.21437/interspeech.2020-1787

Cited by 31 publications

(32 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A challenge for the fusion-based biasing method is that it usually benefits from prefix which may not be available all the time. In [196], class tags are inserted into word transcription during training to enable context aware training. During inference, class tags are used to construct contextual bias finite-state transducer.…”

Section: C) Customizationmentioning

confidence: 99%

Recent Advances in End-to-End Automatic Speech Recognition

Li¹

2021

Preprint

View full text Add to dashboard Cite

Recently, the speech community is seeing a significant trend of moving from deep neural network based hybrid modeling to end-to-end (E2E) modeling for automatic speech recognition (ASR). While E2E models achieve the state-of-the-art results in most benchmarks in terms of ASR accuracy, hybrid models are still used in a large proportion of commercial ASR systems at the current time. There are lots of practical factors that affect the production model deployment decision. Traditional hybrid models, being optimized for production for decades, are usually good at these factors. Without providing excellent solutions to all these factors, it is hard for E2E models to be widely commercialized. In this paper, we will overview the recent advances in E2E models, focusing on technologies addressing those challenges from the industry's perspective.

show abstract

Section: C) Customizationmentioning

confidence: 99%

Recent Advances in End-to-End Automatic Speech Recognition

Li¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…An on-the-fly rescoring mechanism was proposed to adjust the LM weights of n-grams which is relevant to the dynamic context during the decoding procedure in [20]. In [21], the class LM and word mapping algorithm were proposed to achieve the rare entity words recognition with the LAS (Listen, Attend, and Spell) [22] architecture. A shallow-fusion end-to-end biasing method [23] showed the competitive performance with the recurrent neural network transducer (RNN-T) [24] model.…”

Section: Contextual Asr Systemsmentioning

confidence: 99%

A Context-Aware Language Model to Improve the Speech Recognition in Air Traffic Control

et al. 2021

View full text Add to dashboard Cite

Recognizing isolated digits of the flight callsign is an important and challenging task for automatic speech recognition (ASR) in air traffic control (ATC). Fortunately, the flight callsign is a kind of prior ATC knowledge and is available from dynamic contextual information. In this work, we attempt to utilize this prior knowledge to improve the performance of the callsign identification by integrating it into the language model (LM). The proposed approach is named context-aware language model (CALM), which can be applied for both the ASR decoding and rescoring phase. The proposed model is implemented with an encoder–decoder architecture, in which an extra context encoder is proposed to consider the contextual information. A shared embedding layer is designed to capture the correlations between the ASR text and contextual information. The context attention is introduced to learn discriminative representations to support the decoder module. Finally, the proposed approach is validated with an end-to-end ASR model on a multilingual real-world corpus (ATCSpeech). Experimental results demonstrate that the proposed CALM outperforms other baselines for both the ASR and callsign identification task, and can be practically migrated to a real-time environment.

show abstract

“…Since the contextual information is commonly considered as the contextual segments (n-grams, queries and entities) [8,12,14,20,21] in contextual speech recognition, the c-encoder is mainly used to extract the embeddings of these segments. Given a list of N contextual segments Z = {z1, z2, ..., zN }, the c-encoder encodes each segment to a vector.…”

Section: Context Processing Networkmentioning

confidence: 99%

Cif-Based Collaborative Decoding for End-to-End Contextual Speech Recognition

Han

Dong

Zhou

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

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 context information into them for contextual biasing. Though contextual LAS (CLAS) gives an excellent allneural solution, the degree of biasing to given contextual information is not explicitly controllable. In this paper, we focus on incorporating contextual information into the continuous integrate-and-fire (CIF) based model that supports contextual biasing in a more controllable fashion. Specifically, an extra context processing network is introduced to extract contextual embeddings, integrate acoustically relevant contextual information and decode the contextual output distribution, thus forming a collaborative decoding with the decoder of the CIF-based model. Evaluated on the named entity rich evaluation sets of HKUST/AISHELL-2, our method brings relative character error rate (CER) reduction of 8.83%/21.13% and relative named entity character error rate (NE-CER) reduction of 40.14%/51.50% when compared with a strong baseline. Besides, it keeps the performance on original evaluation set without degradation.

show abstract

Class LM and Word Mapping for Contextual Biasing in End-to-End ASR

Cited by 31 publications

References 18 publications

Recent Advances in End-to-End Automatic Speech Recognition

Recent Advances in End-to-End Automatic Speech Recognition

A Context-Aware Language Model to Improve the Speech Recognition in Air Traffic Control

Cif-Based Collaborative Decoding for End-to-End Contextual Speech Recognition

Contact Info

Product

Resources

About