Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing content-based global interactions, while CNNs exploit local features effectively. In this work, we achieve the best of both worlds by studying how to combine convolution neural networks and transformers to model both local and global dependencies of an audio sequence in a parameter-efficient way. To this regard, we propose the convolution-augmented transformer for speech recognition, named Conformer. Conformer significantly outperforms the previous Transformer and CNN based models achieving state-of-the-art accuracies. On the widely used LibriSpeech benchmark, our model achieves WER of 2.1%/4.3% without using a language model and 1.9%/3.9% with an external language model on test/testother. We also observe competitive performance of 2.7%/6.3% with a small model of only 10M parameters.

Conformer: Convolution-augmented Transformer for Speech Recognition

In embodiments of the present invention improved capabilities are described for managing digital rights management (DRM) protected content sharing in a networked secure collaborative computer data exchange environment through a secure exchange facility managed by an intermediate organizational entity amongst users of a plurality of other organizational entities, wherein computer data content and access rights for the computer data content is shared between a first and second user, the computer data content and access rights for the computer data content are transformed into a DRM protected computer data content through communications with a DRM engine, wherein the DRM engine is selected based on a content type of the computer data content, and the DRM engine is provided by an entity other than the intermediate organizational entity and other than any of the plurality of other organizational entities.

Systems and methods of secure data exchange

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel CNN-RNN-transducer architecture, which we call ContextNet. ContextNet features a fully convolutional encoder that incorporates global context information into convolution layers by adding squeeze-and-excitation modules. In addition, we propose a simple scaling method that scales the widths of ContextNet that achieves good trade-off between computation and accuracy. We demonstrate that on the widely used LibriSpeech benchmark, ContextNet achieves a word error rate (WER) of 2.1%/4.6% without external language model (LM), 1.9%/4.1% with LM and 2.9%/7.0% with only 10M parameters on the clean/noisy LibriSpeech test sets. This compares to the previous best published system of 2.0%/4.6% with LM and 3.9%/11.3% with 20M parameters. The superiority of the proposed ContextNet model is also verified on a much larger internal dataset.

ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops speaking. In this paper, we develop a first-pass Recurrent Neural Network Transducer (RNN-T) model and a second-pass Listen, Attend, Spell (LAS) rescorer that surpasses a conventional model in both quality and latency. On the quality side, we incorporate a large number of utterances across varied domains [1] to increase acoustic diversity and the vocabulary seen by the model. We also train with accented English speech to make the model more robust to different pronunciations. In addition, given the increased amount of training data, we explore a varied learning rate schedule. On the latency front, we explore using the end-of-sentence decision emitted by the RNN-T model to close the microphone, and also introduce various optimizations to improve the speed of LAS rescoring. Overall, we find that RNN-T+LAS offers a better WER and latency tradeoff compared to a conventional model. For example, for the same latency, RNN-T+LAS obtains a 8% relative improvement in WER, while being more than 400-times smaller in model size.

A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency

According to one general aspect, a method for playing, in an offline mode, a media file may include receiving, by a web browser operating in an online mode and from a content server, a media file and at least one advertisement associated with the media file The method may further include caching, within a local file system, the media file and the at least one advertisement The method may also include playing, in an offline mode, the cached media file and the cached at least one advertisement The method also comprise detecting a user interaction, while in an offline mode, with the at least one advertisement The method may include caching the user interaction for further processing when in an online mode

Cloud based media player and offline media access

System and computer program products allows renderer in UPnP network the capability of rendering general Internet content of static or dynamic nature, which renderer was not designed to render in the contents' original data format and file type. System queries all devices on local network, queries specific remote servers over Internet, and retrieves data feeds from remote sources. Queried and retrieved data not in a format and file type that can be rendered by renderer is loaded into templates and turned into a format and file type acceptable by renderer. Queried and retrieved data in proper format and file type is organized in custom format and made available for rendering to renderer. System has capability of transmitting content or metadata of content within devices on local network to a hosting service over Internet. Additionally, a second local network has capability of accessing content stored on first local network.

Organizing and publishing assets in upnp networks

Systems and computer program products for allowing a renderer in a UPnP network the capability of being able to render general Internet content of static or dynamic nature, which the renderer was not designed to render in the contents original data format and file type. The system queries all devices on the local network, queries specific remote servers over the Internet, and retrieves data feeds from remote sources. The queried and retrieved data that is not in a format and file type that can be rendered by the renderer is loaded into a template and turned into a format and file type acceptable by the renderer. The queried and retrieved data in the proper format and file type is organized in a custom format and made available for rendering to the renderer. The system has the capability of transmitting content or the metadata of the content within the devices on the local network to a hosting service over the Internet. Additionally, a second local network has the capability of accessing the content stored on the first local network.

Sharing Assets Between UPnP Networks

System and computer program products for allowing a renderer in a UPnP network the capability of being able to render general Internet content, which the renderer was not designed to render in the contents original data format and file type. The system queries all devices on the local network, queries specific remote servers over the Internet, and retrieves data feeds from remote sources. The queried and retrieved data that is not in a format and file type that can be rendered by the renderer is loaded into a template and turned into a format and file type acceptable by the renderer. The queried and retrieved data in the proper format and file type is organized in a custom format and made available for rendering to the renderer. The system has the capability of transmitting content or the metadata of the content within the devices on the local network to a hosting service over the Internet. Additionally, a second local network has the capability of accessing the content stored on the first local network.

Publishing Assets Of Dynamic Nature In UPnP Networks

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

David Garcia

Author Tools

Chat about Author