113 citations · 173 across the 12 of their papers we have counts for
13 papers
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
Yu Zhang, Wei Han, James Qin +24
We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages. This is achieved by pre-training the enc…
G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR
Gary Wang, Ekin D. Cubuk, Andrew Rosenberg +6
Data augmentation is a ubiquitous technique used to provide robustness to automatic speech recognition (ASR) training. However, even as so much of the ASR training process has beco…
Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR
Zhehuai Chen, Ankur Bapna, Andrew Rosenberg +4
Training state-of-the-art Automated Speech Recognition (ASR) models typically requires a substantial amount of transcribed speech. In this work, we demonstrate that a modality-matc…
Modular Hybrid Autoregressive Transducer
Zhong Meng, Tongzhou Chen, Rohit Prabhavalkar +10
Text-only adaptation of a transducer model remains challenging for end-to-end speech recognition since the transducer has no clearly separated acoustic model (AM), language model (…
Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition
Kartik Audhkhasi, Yinghui Huang, Bhuvana Ramabhadran +1
Attention layers are an integral part of modern end-to-end automatic speech recognition systems, for instance as part of the Transformer or Conformer architecture. Attention is typ…
MAESTRO: Matched Speech Text Representations through Modality Matching
Zhehuai Chen, Yu Zhang, Andrew Rosenberg +4
We present Maestro, a self-supervised training method to unify representations learnt from speech and text modalities. Self-supervised learning from speech signals aims to learn th…
A Scalable Model Specialization Framework for Training and Inference using Submodels and its Application to Speech Model Personalization
Fadi Biadsy, Youzheng Chen, Xia Zhang +3
Model fine-tuning and adaptation have become a common approach for model specialization for downstream tasks or domains. Fine-tuning the entire model or a subset of the parameters…
Ask2Mask: Guided Data Selection for Masked Speech Modeling
Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran +2
Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improv…
Injecting Text in Self-Supervised Speech Pretraining
Zhehuai Chen, Yu Zhang, Andrew Rosenberg +3
Self-supervised pretraining for Automated Speech Recognition (ASR) has shown varied degrees of success. In this paper, we propose to jointly learn representations during pretrainin…
Speech Recognition with Augmented Synthesized Speech
Andrew Rosenberg, Yu Zhang, Bhuvana Ramabhadran +4
Recent success of the Tacotron speech synthesis architecture and its variants in producing natural sounding multi-speaker synthesized speech has raised the exciting possibility of…
Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation
Fadi Biadsy, Ron J. Weiss, Pedro J. Moreno +2
We describe Parrotron, an end-to-end-trained speech-to-speech conversion model that maps an input spectrogram directly to another spectrogram, without utilizing any intermediate di…
From Audio to Semantics: Approaches to end-to-end spoken language understanding
Parisa Haghani, Arun Narayanan, Michiel Bacchiani +6
Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural languag…
Multilingual Speech Recognition With A Single End-To-End Model
Shubham Toshniwal, Tara N. Sainath, Ron J. Weiss +4
Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the sub-word unit, lexicon and word inventories are typically…