research
∙
08/11/2023
Improving Joint Speech-Text Representations Without Alignment
The last year has seen astonishing progress in text-prompted image gener...
share
research
∙
06/01/2023
How to Estimate Model Transferability of Pre-Trained Speech Models?
In this work, we introduce a “score-based assessment” framework for esti...
research
∙
04/19/2023
A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale
Unpaired text and audio injection have emerged as dominant methods for i...
research
∙
03/31/2023
Lego-Features: Exporting modular encoder features for streaming and deliberation ASR
In end-to-end (E2E) speech recognition models, a representational tight-...
research
∙
03/15/2023
Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models
Continued improvements in machine learning techniques offer exciting new...
research
∙
03/03/2023
End-to-End Speech Recognition: A Survey
In the last decade of automatic speech recognition (ASR) research, the i...
research
∙
03/02/2023
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
We introduce the Universal Speech Model (USM), a single large model that...
research
∙
02/16/2023
JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition
We propose JEIT, a joint end-to-end (E2E) model and internal language mo...
research
∙
01/19/2023
From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition
In this work, we propose a new parameter-efficient learning framework ba...
research
∙
01/11/2023
Dual Learning for Large Vocabulary On-Device ASR
Dual learning is a paradigm for semi-supervised machine learning that se...
research
∙
11/28/2022
E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model
We explore unifying a neural segmenter with two-pass cascaded encoder AS...
research
∙
10/31/2022
Modular Hybrid Autoregressive Transducer
Text-only adaptation of a transducer model remains challenging for end-t...
research
∙
10/13/2022
JOIST: A Joint Speech and Text Streaming Model For ASR
We present JOIST, an algorithm to train a streaming, cascaded, encoder e...
research
∙
06/29/2022
Improving Deliberation by Text-Only and Semi-Supervised Training
Text-only and semi-supervised training based on audio-only data has gain...
research
∙
04/22/2022
E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR
Improving the performance of end-to-end ASR models on long utterances ra...
research
∙
04/15/2022
Improving Rare Word Recognition with LM-aware MWER Training
Language models (LMs) significantly improve the recognition accuracy of ...
research
∙
04/13/2022
A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
In this paper, we propose a dynamic cascaded encoder Automatic Speech Re...
research
∙
01/28/2022
Neural-FST Class Language Model for End-to-End Speech Recognition
We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech...
research
∙
10/08/2021
Input Length Matters: An Empirical Study Of RNN-T And MWER Training For Long-form Telephony Speech Recognition
End-to-end models have achieved state-of-the-art results on several auto...
research
∙
06/01/2021
A Neural Acoustic Echo Canceller Optimized Using An Automatic Speech Recognizer And Large Scale Synthetic Data
We consider the problem of recognizing speech utterances spoken to a dev...
research
∙
04/06/2021
Dissecting User-Perceived Latency of On-Device E2E Speech Recognition
As speech-enabled devices such as smartphones and smart speakers become ...
research
∙
04/05/2021
Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency
We propose a dynamic encoder transducer (DET) for on-device speech recog...
research
∙
03/11/2021
Learning Word-Level Confidence For Subword End-to-End ASR
We study the problem of word-level confidence estimation in subword-base...
research
∙
12/12/2020
Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging
End-to-end models that condition the output label sequence on all previo...
research
∙
10/27/2020
Cascaded encoders for unifying streaming and non-streaming ASR
End-to-end (E2E) automatic speech recognition (ASR) models, by now, have...
research
∙
10/20/2020
Replacing Human Audio with Synthetic Audio for On-device Unspoken Punctuation Prediction
We present a novel multi-modal unspoken punctuation prediction system fo...
research
∙
05/07/2020
RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions
In recent years, all-neural end-to-end approaches have obtained state-of...
research
∙
03/28/2020
A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Thus far, end-to-end (E2E) models have not been shown to outperform stat...
research
∙
03/17/2020
Deliberation Model Based Two-Pass End-to-End Speech Recognition
End-to-end (E2E) models have made rapid progress in automatic speech rec...
research
∙
11/06/2019
A comparison of end-to-end models for long-form speech recognition
End-to-end automatic speech recognition (ASR) models, including both att...
research
∙
10/24/2019
Recognizing long-form speech using streaming end-to-end models
All-neural end-to-end (E2E) automatic speech recognition (ASR) systems t...
research
∙
08/29/2019
Two-Pass End-to-End Speech Recognition
The requirements for many applications of state-of-the-art speech recogn...
research
∙
06/21/2019
Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models
Contextual automatic speech recognition, i.e., biasing recognition towar...
research
∙
02/21/2019
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Lingvo is a Tensorflow framework offering a complete solution for collab...
research
∙
02/05/2019
Model Unit Exploration for Sequence-to-Sequence Speech Recognition
We evaluate attention-based encoder-decoder models along two dimensions:...
research
∙
11/15/2018
Streaming End-to-end Speech Recognition For Mobile Devices
End-to-end (E2E) models, which directly predict output character sequenc...
research
∙
09/24/2018
From Audio to Semantics: Approaches to end-to-end spoken language understanding
Conventional spoken language understanding systems consist of two main c...
research
∙
08/07/2018
Deep context: end-to-end contextual speech recognition
In automatic speech recognition (ASR) what a user says depends on the pa...
research
∙
01/02/2018
Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducer
We investigate training end-to-end speech recognition models with the re...
research
∙
12/06/2017
An analysis of incorporating an external language model into a sequence-to-sequence model
Attention-based sequence-to-sequence models for automatic speech recogni...
research
∙
12/05/2017
No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models
For decades, context-dependent phonemes have been the dominant sub-word ...
research
∙
12/05/2017
Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Models
Sequence-to-sequence models, such as attention-based models in automatic...
research
∙
12/05/2017
Improving the Performance of Online Neural Transducer Models
Having a sequence-to-sequence model which can operate in an online fashi...
research
∙
12/05/2017
State-of-the-art Speech Recognition With Sequence-to-Sequence Models
Attention-based encoder-decoder architectures such as Listen, Attend, an...
research
∙
11/15/2017
Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition
We investigate the effectiveness of generative adversarial networks (GAN...
research
∙
10/26/2017
Streaming Small-Footprint Keyword Spotting using Sequence-to-Sequence Models
We develop streaming keyword spotting systems using a recurrent neural n...
research
∙
07/15/2016
On the efficient representation and execution of deep acoustic models
In this paper we present a simple and computationally efficient quantiza...
research
∙
03/25/2016
On the Compression of Recurrent Neural Networks with an Application to LVCSR acoustic modeling for Embedded Speech Recognition
We study the problem of compressing recurrent neural networks (RNNs). In...
research
∙
03/10/2016