research
∙
08/14/2023
O-1: Self-training with Oracle and 1-best Hypothesis
We introduce O-1, a new self-training objective to reduce training bias ...
share
research
∙
08/14/2023
Using Text Injection to Improve Recognition of Personal Identifiers in Speech
Accurate recognition of specific categories, such as persons' names, dat...
research
∙
06/13/2023
Large-scale Language Model Rescoring on Long-form Data
In this work, we study the impact of Large-scale Language Models (LLM) o...
research
∙
04/27/2023
Understanding Shared Speech-Text Representations
Recently, a number of approaches to train speech models by incorpo-ratin...
research
∙
03/10/2023
Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss
This work studies knowledge distillation (KD) and addresses its constrai...
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
∙
10/31/2022
Modular Hybrid Autoregressive Transducer
Text-only adaptation of a transducer model remains challenging for end-t...
research
∙
10/27/2022
Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech
This paper proposes Virtuoso, a massively multilingual speech-text joint...
research
∙
10/19/2022
G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR
Data augmentation is a ubiquitous technique used to provide robustness t...
research
∙
10/18/2022
Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR
Training state-of-the-art Automated Speech Recognition (ASR) models typi...
research
∙
09/15/2022
Non-Parallel Voice Conversion for ASR Augmentation
Automatic speech recognition (ASR) needs to be robust to speaker differe...
research
∙
09/13/2022
Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition
Attention layers are an integral part of modern end-to-end automatic spe...
research
∙
05/16/2022
Accented Speech Recognition: Benchmarking, Pre-training, and Diverse Data
Building inclusive speech recognition systems is a crucial step towards ...
research
∙
04/15/2022
Improving Rare Word Recognition with LM-aware MWER Training
Language models (LMs) significantly improve the recognition accuracy of ...
research
∙
04/07/2022
MAESTRO: Matched Speech Text Representations through Modality Matching
We present Maestro, a self-supervised training method to unify represent...
research
∙
02/24/2022
Ask2Mask: Guided Data Selection for Masked Speech Modeling
Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn ...
research
∙
09/27/2021
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 spee...
research
∙
08/27/2021
Injecting Text in Self-Supervised Speech Pretraining
Self-supervised pretraining for Automated Speech Recognition (ASR) has s...
research
∙
08/13/2020
LSTM Acoustic Models Learn to Align and Pronounce with Graphemes
Automated speech recognition coverage of the world's languages continues...
research
∙
04/20/2020
Language-agnostic Multilingual Modeling
Multilingual Automated Speech Recognition (ASR) systems allow for the jo...
research
∙
02/06/2020
Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior
Recent neural text-to-speech (TTS) models with fine-grained latent featu...
research
∙
09/25/2019
Speech Recognition with Augmented Synthesized Speech
Recent success of the Tacotron speech synthesis architecture and its var...
research
∙
09/11/2019
Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model
Multilingual end-to-end (E2E) models have shown great promise in expansi...
research
∙
07/09/2019
Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning
We present a multispeaker, multilingual text-to-speech (TTS) synthesis m...
research
∙
02/07/2018
Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition
The performance of automatic speech recognition systems degrades with in...
research
∙
12/08/2017
Building competitive direct acoustics-to-word models for English conversational speech recognition
Direct acoustics-to-word (A2W) models in the end-to-end paradigm have re...
research
∙
09/19/2017
Language Modeling with Highway LSTM
Language models (LMs) based on Long Short Term Memory (LSTM) have shown ...
research
∙
03/22/2017
Direct Acoustics-to-Word Models for English Conversational Speech Recognition
Recent work on end-to-end automatic speech recognition (ASR) has shown t...
research
∙
03/06/2017
English Conversational Telephone Speech Recognition by Humans and Machines
One of the most difficult speech recognition tasks is accurate recogniti...
research
∙
01/13/2017
End-to-End ASR-free Keyword Search from Speech
End-to-end (E2E) systems have achieved competitive results compared to c...
research
∙
11/27/2016
Invariant Representations for Noisy Speech Recognition
Modern automatic speech recognition (ASR) systems need to be robust unde...
research
∙
12/22/2014
Diverse Embedding Neural Network Language Models
We propose Diverse Embedding Neural Network (DENN), a novel architecture...
research
∙
12/28/2013
Generalized Ambiguity Decomposition for Understanding Ensemble Diversity
Diversity or complementarity of experts in ensemble pattern recognition ...
research
∙
09/05/2013
Accelerating Hessian-free optimization for deep neural networks by implicit preconditioning and sampling
Hessian-free training has become a popular parallel second or- der optim...
research
∙
09/05/2013