Streaming End-to-end Speech Recognition For Mobile Devices

Yanzhang He, Tara N. Sainath, Rohit Prabhavalkar

Show all 20 authors

Ian McGraw, Raziel Alvarez, Ding Zhao, David Rybach, Anjuli Kannan, Yonghui Wu, Ruoming Pang, Qiao Liang, Deepti Bhatia, Yuan Shangguan, Bo Li, Golan Pundak, Khe Chai Sim, Tom Bagby, Shuo-yiin Chang, Kanishka Rao, Alexander Gruenstein

2018 · arXiv

Psychology Machine learning

Read the paper

HN score: 0
Mentions: 4
Readers: 3
Months: 4

What’s in a score?

From the abstract

End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models must decode speech utterances in a streaming fashion, in real time; they must be robust to the long tail of use cases; they must be able to leverage user-specific context (e.g., contact lists); and above all, they must be extremely accurate. In this work, we describe our efforts at building an E2E speech recognizer using a recurrent neural network transducer. In experimental evaluations, we find that the proposed approach can outperform a conventional CTC-based model in terms of both latency and accuracy in a number of evaluation categories.

Metadata: arXiv. Abstracts retain their original authors’ rights.

In the conversation

Original HN comments, with labels from simple text rules. A label describes the whole comment and may miss context or irony. Read the discussion to make up your own mind. About the labels

4 selected excerpts · 4 total mentions

Show

iceychrisNov 15, 2020

Neutral mention · rule

Hey HN! I've been working on this for a while now. While there are other on-premise solutions using older models such as DeepSpeech [0], I haven't found a deployable project supporting multiple languages using the recent RNN-T Architecture [1]. Please note that this does not achieve SotA performance. Also, I've only trained it on one GPU so there might be room for improvement. Edit: Don't expect good performance :D this is still in early stage development. I am looking for contributers :) [0] https://github.com/mozilla/DeepSpeech [1] https://arxiv.org/abs/1811.06621

Original comment Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

polymorph1smJul 6, 2020

Neutral mention · rule

Online decoding in Kaldi uses GMM (or NN+GMM hybrid) where this repo focus in end to end approach using deep LSTM (similar to Google Pixel's offline speech to text [1]). [1] https://arxiv.org/pdf/1811.06621.pdf

Original comment Show HN: Open-source online speech recognition

walterbellNov 5, 2019

Neutral mention · rule

Google published research [1][2] on offline recognition and it was rolled out earlier in 2019. Model size for English is claimed to be under 100MB, https://techcrunch.com/2019/03/12/googles-new-voice-recognit... [1] https://arxiv.org/pdf/1603.03185.pdf (2016) [2] https://arxiv.org/pdf/1811.06621.pdf (2018)

Original comment Bringing Google Live Transcribe's Speech Engine to Everyone

walterbellMay 18, 2019

Neutral mention · rule

Google mentioned at I/O that speech recognition will soon (this summer?) be performed locally on Android devices, with no voice data being sent to Google, because they have been able to reduce the size of the model dramatically. Is that related to federated learning? Paper: https://arxiv.org/abs/1811.06621

Original comment Federated Learning

Keep following the thread.

Sparks of Artificial General Intelligence: Early experiments with GPT-4

Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan +11

Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition.

Language models Psychology Mathematics

60 mentions14 months

3.5HN score

2020arXiv

Language Models are Few-Shot Learners

Tom B. Brown, Benjamin Mann, Nick Ryder +28

Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task.

Language models Machine learning

83 mentions35 months

3HN score

2016arXiv

Understanding deep learning requires rethinking generalization

Chiyuan Zhang, Samy Bengio, Moritz Hardt +2

Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance.

Machine learning Computer vision Statistics & probability

16 mentions14 months

2.5HN score

2018arXiv

Talent vs Luck: the role of randomness in success and failure

A. Pluchino. A. E. Biondo, A. Rapisarda

The largely dominant meritocratic paradigm of highly competitive Western cultures is rooted on the belief that success is due mainly, if not exclusively, to personal qualities such as talent, intelligence, skills, efforts or risk taking.

Psychology

16 mentions14 months

2.5HN score