Search Results for author:
Found 29 papers, 1 papers with code
Streaming End-to-end Speech Recognition For Mobile Devices
End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition.
Understanding Recurrent Neural State Using Memory Signatures
We demonstrate this method's usefulness in revealing information divergence in the bases of recurrent factorized kernels, visualizing the character-level differences between the memory of n-gram and recurrent language models, and extracting knowledge of history encoded in the layers of grapheme-based end-to-end ASR networks.
Toward domain-invariant speech recognition via large scale training
More importantly, such models generalize better to unseen conditions and allow for rapid adaptation -- we show that by using as little as 10 hours of data from a new domain, an adapted domain-invariant model can match performance of a domain-specific model trained from scratch using 70 times as much data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model
Sequence-to-sequence models provide a simple and elegant solution for building speech recognition systems by folding separate components of a typical system, namely acoustic (AM), pronunciation (PM) and language (LM) models into a single neural network.
An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models
Speaker-independent speech recognition systems trained with data from many users are generally robust against speaker variability and work well for a large population of speakers.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities
With speech input, if the user corrects only the names, the name recall rate improves to 64. 4%.
Low-rank Gradient Approximation For Memory-Efficient On-device Training of Deep Neural Network
Training machine learning models on mobile devices has the potential of improving both privacy and accuracy of the models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech
While current state-of-the-art Automatic Speech Recognition (ASR) systems achieve high accuracy on typical speech, they suffer from significant performance degradation on disordered speech and other atypical speech patterns.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio.
Ranked #1 on
Speech Recognition
on Common Voice
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning
Self- and semi-supervised learning methods have been actively investigated to reduce labeled training data or enhance the model performance.
Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device
These models are typically trained on the server using transcribed speech data.
Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition
Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can yield an even better recognition result.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Joint Unsupervised and Supervised Training for Multilingual ASR
Our average WER of all languages outperforms average monolingual baseline by 33. 3%, and the state-of-the-art 2-stage XLSR by 32%.
Pseudo Label Is Better Than Human Label
State-of-the-art automatic speech recognition (ASR) systems are trained with tens of thousands of hours of labeled speech data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
UserLibri: A Dataset for ASR Personalization Using Only Text
We experiment on a user-clustered LibriSpeech corpus, supplemented with personalized text-only data for each user from Project Gutenberg.
Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning
Almost none of the 2, 000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR
Knowledge distillation is an effective machine learning technique to transfer knowledge from a teacher model to a smaller student model, especially with unlabeled data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Resource-Efficient Transfer Learning From Speech Foundation Model Using Hierarchical Feature Fusion
Experimental results show that the proposed method can achieve better performance on speech recognition task than existing algorithms with fewer number of trainable parameters, less computational memory cost and faster training speed.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Efficient Domain Adaptation for Speech Foundation Models
The FM encoder adapter and decoder are then finetuned to the target domain with a small amount of supervised in-domain data.
Edit Distance based RL for RNNT decoding
RNN-T is currently considered the industry standard in ASR due to its exceptional WERs in various benchmark tests and its ability to support seamless streaming and longform transcription.
Improving Speech Recognition for African American English With Audio Classification
By combining the classifier output with coarse geographic information, we can select a subset of utterances from a large corpus of untranscribed short-form queries for semi-supervised learning at scale.
Massive End-to-end Models for Short Search Queries
In this work, we investigate two popular end-to-end automatic speech recognition (ASR) models, namely Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), for offline recognition of voice search queries, with up to 2B model parameters.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm
Contextual biasing refers to the problem of biasing the automatic speech recognition (ASR) systems towards rare entities that are relevant to the specific user or application scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning
In many applications of federated learning (FL), clients desire models that are personalized using their local data, yet are also robust in the sense that they retain general global knowledge.
Hierarchical Recurrent Adapters for Efficient Multi-Task Adaptation of Large Speech Models
However, their per-task parameter overhead is considered still high when the number of downstream tasks to adapt for is large.
TransformerFAM: Feedback attention is working memory
While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs.
