Search Results for author:
Found 17 papers, 0 papers with code
Towards measuring fairness in speech recognition: Fair-Speech dataset
The current public datasets for speech recognition (ASR) tend not to focus specifically on the fairness aspect, such as performance across different demographic groups.
Mitigating Unintended Memorization in Language Models via Alternating Teaching
Recent research has shown that language models have a tendency to memorize rare or unique sequences in the training corpora which can thus leak sensitive attributes of user data.
Group Personalized Federated Learning
Federated learning (FL) can help promote data privacy by training a shared model in a de-centralized manner on the physical devices of clients.
Modeling Dependent Structure for Utterances in ASR Evaluation
In this paper, we present graphical lasso based methods to explicitly model such dependency and estimate uncorrelated blocks of utterances in a rigorous way, after which blockwise bootstrap is applied on top of the inferred blocks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Neural-FST Class Language Model for End-to-End Speech Recognition
We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework.
Private Language Model Adaptation for Speech Recognition
Speech model adaptation is crucial to handle the discrepancy between server-side proxy training data and actual data received on local devices of users.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Model-Based Approach for Measuring the Fairness in ASR
The issue of fairness arises when the automatic speech recognition (ASR) systems do not perform equally well for all subgroups of the population.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
On lattice-free boosted MMI training of HMM and CTC-based full-context ASR models
Hybrid automatic speech recognition (ASR) models are typically sequentially trained with CTC or LF-MMI criteria.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models
We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent.
Federated Marginal Personalization for ASR Rescoring
Our presented approach can overcome the limitations of federated fine-tuning and efficiently learn personalized NNLMs on devices.
Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR
In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Statistical Testing on ASR Performance via Blockwise Bootstrap
A common question being raised in automatic speech recognition (ASR) evaluations is how reliable is an observed word error rate (WER) improvement comparing two ASR systems, where statistical hypothesis testing and confidence interval (CI) can be utilized to tell whether this improvement is real or only due to random chance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Improving N-gram Language Models with Pre-trained Deep Transformer
Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference.
Training ASR models by Generation of Contextual Information
Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data.
An Empirical Study of Efficient ASR Rescoring with Transformers
In particular, our experiments on a video speech recognition dataset show that we are able to achieve WERRs ranging from 6. 46% to 7. 17% while only with 5. 5% to 11. 9% parameter sizes of the well-known large GPT model [1], whose WERR with rescoring on the same dataset is 7. 58%.
Efficient Dynamic WFST Decoding for Personalized Language Models
A second layer is a private cache that caches the graph that represents the personalized language model, which is only shared by the utterances from a particular user.
Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models
We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent.
