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 …

We present JOIST, an algorithm to train a streaming, cascaded, encoder end-to-end (E2E)
model with both speech-text paired inputs, and text-only unpaired inputs. Unlike previous …

We improve on the popular conformer architecture by replacing the depthwise temporal
convolutions with diagonal state space (DSS) models. DSS is a recently introduced variant …

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 …

Attention-based biasing techniques for end-to-end ASR systems are able to achieve large
accuracy gains without requiring the inference algorithm adjustments and parameter tuning …

Speech data from different domains has distinct acoustic and linguistic characteristics. It is
common to train a single multidomain model such as a Conformer transducer for speech …

In this paper, we propose a dynamic cascaded encoder Automatic Speech Recognition
(ASR) model, which unifies models for different deployment scenarios. Moreover, the model …

There is growing interest in unifying the streaming and full-context automatic speech
recognition (ASR) networks into a single end-to-end ASR model to simplify the model …

Text-only and semi-supervised training based on audio-only data has gained popularity
recently due to the wide availability of unlabeled text and speech data. In this work, we …

For on-device automatic speech recognition (ASR), quantization aware training (QAT) is
ubiquitous to achieve the trade-off between model predictive performance and efficiency …