This portal is to open public enhancement requests against products and services offered by the IBM Data & AI organization. To view all of your ideas submitted to IBM, create and manage groups of Ideas, or create an idea explicitly set to be either visible by all (public) or visible only to you and IBM (private), use the IBM Unified Ideas Portal (https://ideas.ibm.com).
Shape the future of IBM!
We invite you to shape the future of IBM, including product roadmaps, by submitting ideas that matter to you the most. Here's how it works:
Search existing ideas
Start by searching and reviewing ideas and requests to enhance a product or service. Take a look at ideas others have posted, and add a comment, vote, or subscribe to updates on them if they matter to you. If you can't find what you are looking for,
Post your ideas
Post ideas and requests to enhance a product or service. Take a look at ideas others have posted and upvote them if they matter to you,
Post an idea
Upvote ideas that matter most to you
Get feedback from the IBM team to refine your idea
Specific links you will want to bookmark for future use
Welcome to the IBM Ideas Portal (https://www.ibm.com/ideas) - Use this site to find out additional information and details about the IBM Ideas process and statuses.
IBM Unified Ideas Portal (https://ideas.ibm.com) - Use this site to view all of your ideas, create new ideas for any IBM product, or search for ideas across all of IBM.
ideasibm@us.ibm.com - Use this email to suggest enhancements to the Ideas process or request help from IBM for submitting your Ideas.
IBM Employees should enter Ideas at https://ideas.ibm.com
STT on CP4D offering
Hybrid Model is not just Offline speech -- Need a Hybrid Conversation Framework (that should include STT, Conversation, NLU, TTS) - an Edge Model. Low energy keyword activation can be an first phase of this entire Edge Model Program. For this we would need to know details of how it can be exposed - i.e. open source, library, compiled code and what programming paradigm will it support: (i.e. IOS, Android, Raspberry Pi, Auto-specific models?)
Right now this work will not be prioritized for Q4 and Q1. We will start having strategic discussions on this in Q4 and have a goal to have something on roadmap by end or Q4 for edge computing.
The issue is broader than just speech, the WPA team would like to have (limited) conversational capability offline.
Most relevant speech related task:
- create offline STT SDK
-- well-defined API
-- documentation
-- offline capabilities
--- low-energy keyword activation
--- speech barge-in into TTS
--- platform support - most importantly BLAS (or equivalent) libraries on ASM level
-- automotive acoustic models
-- tools for LM pruning (basic LM smaller than for service)
-- more languages :)
-- platform CI
- create offline TTS SDK
-- well-defined API
-- documentation
-- offline capabilities
--- CELP voice support
--- smaller CELP voices (tooling)
--- RNN prosody & phrasebreak speed up / reimplementation
--- solve expressive for embedded
--- parametric (voice transformation) for embedded