Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

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 …

In the last decade of automatic speech recognition (ASR) research, the introduction of deep
learning has brought considerable reductions in word error rate of more than 50% relative …

End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for
streaming speech recognition [1] across many dimensions, including quality (as measured …

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as
quickly and accurately as possible, while full-context ASR waits for the completion of a full …

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 …

Recent work on self-supervised pre-training focus on leveraging large-scale unlabeled
speech data to build robust end-to-end (E2E) acoustic models (AM) that can be later fine …

Language identification is critical for many downstream tasks in automatic speech
recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an …

On-device end-to-end (E2E) models have shown improvements over a conventional model
on Search test sets in both quality, as measured by Word Error Rate (WER)[1], and latency …

State-of-the-art automatic speech recognition (ASR) systems are trained with tens of
thousands of hours of labeled speech data. Human transcription is expensive and time …