Search Results for author:
Found 15 papers, 1 papers with code
USTED: Improving ASR with a Unified Speech and Text Encoder-Decoder
There has been a recent focus on training E2E ASR models that get the performance benefits of external text data without incurring the extra cost of evaluating an external language model at inference time.
RescoreBERT: Discriminative Speech Recognition Rescoring with BERT
Specifically, training a bidirectional model like BERT on a discriminative objective such as minimum WER (MWER) has not been explored.
Automatic Speech Recognition
Natural Language Understanding
+1
A Likelihood Ratio based Domain Adaptation Method for E2E Models
In this work, we explore a contextual biasing approach using likelihood-ratio that leverages text data sources to adapt RNN-T model to new domains and entities.
Domain Prompts: Towards memory and compute efficient domain adaptation of ASR systems
Automatic Speech Recognition (ASR) systems have found their use in numerous industrial applications in very diverse domains creating a need to adapt to new domains with small memory and deployment overhead.
Lattention: Lattice-attention in ASR rescoring
The rescoring model with attention to lattices achieves 4-5% relative word error rate reduction over first-pass and 6-8% with attention to both lattices and acoustic features.
Automatic Speech Recognition
Spoken Language Understanding
+1
Prompt-tuning in ASR systems for efficient domain-adaptation
In this work, we overcome the problem using prompt-tuning, a methodology that trains a small number of domain token embedding parameters to prime a transformer-based LM to a particular domain.
Attention-based Contextual Language Model Adaptation for Speech Recognition
When applied to a large de-identified dataset of utterances collected by a popular voice assistant platform, our method reduces perplexity by 7. 0% relative over a standard LM that does not incorporate contextual information.
Personalization Strategies for End-to-End Speech Recognition Systems
We also describe a novel second-pass de-biasing approach: used in conjunction with a first-pass shallow fusion that optimizes on oracle WER, we can achieve an additional 14% improvement on personalized content recognition, and even improve accuracy for the general use case by up to 2. 5%.
Domain-aware Neural Language Models for Speech Recognition
As voice assistants become more ubiquitous, they are increasingly expected to support and perform well on a wide variety of use-cases across different domains.
Improving accuracy of rare words for RNN-Transducer through unigram shallow fusion
We show that this simple method can improve performance on rare words by 3. 7% WER relative without degradation on general test set, and the improvement from USF is additive to any additional language model based rescoring.
Multi-task Language Modeling for Improving Speech Recognition of Rare Words
We show that our rescoring model trained with these additional tasks outperforms the baseline rescoring model, trained with only the language modeling task, by 1. 4% on a general test and by 2. 6% on a rare word test set in terms of word-error-rate relative (WERR).
Audio-attention discriminative language model for ASR rescoring
In this work, we propose to combine the benefits of end-to-end approaches with a conventional system using an attention-based discriminative language model that learns to rescore the output of a first-pass ASR system.
Scalable language model adaptation for spoken dialogue systems
New application intents and interaction types are released for these systems over time, imposing challenges to adapt the LMs since the existing training data is no longer sufficient to model the future user interactions.
Contextual Language Model Adaptation for Conversational Agents
Statistical language models (LM) play a key role in Automatic Speech Recognition (ASR) systems used by conversational agents.
Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
This paper presents the design of the machine learning architecture that underlies the Alexa Skills Kit (ASK) a large scale Spoken Language Understanding (SLU) Software Development Kit (SDK) that enables developers to extend the capabilities of Amazon's virtual assistant, Alexa.
