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:
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
Help IBM prioritize your ideas and requests
The IBM team may need your help to refine the ideas so they may ask for more information or feedback. The product management team will then decide if they can begin working on your idea. If they can start during the next development cycle, they will put the idea on the priority list. Each team at IBM works on a different schedule, where some ideas can be implemented right away, others may be placed on a different schedule.
Receive notification on the decision
Some ideas can be implemented at IBM, while others may not fit within the development plans for the product. In either case, the team will let you know as soon as possible. In some cases, we may be able to find alternatives for ideas which cannot be implemented in a reasonable time.
Ability to move fully trained STT models between separate instances (i.e. DEV vs. PROD or separate accounts)
Customers for best practice reasons keep environments separate (DEV vs. PROD) for security, performance, testing & availability of the model.
Training STT models can take hours to train.
Not utilizing fully trained models results in delay...
I have a customer that is a daily magazine on the web as well as a podcast network. They offer analysis and commentary about politics, news, business, technology, and culture. They are considering our IBM Speech to Text (STT) solution to provide a...
Improve API response structure for timestamps and word_confidence within STT SpeechRecognitionAlternative model
As part of the response from making a POST to the v1/recognize endpoint in the Speech to Text service, the user receives an array of "alternatives". Within these "alternatives" objects, there are two arrays called "word_confidence" and "transcrip...
Requesting for IBM Bluemix Watson Text-to-speech supports Mandarin and Cantonese
IBM Bluemix Watson Text-to-speech service supports Mandarin and Cantonese.
IBM Bluemix Watson Speech-to-Text support Mandarin, it's logical that Text-to-speech support Mandarin.
Meanwhile, there is a niche market on STT/TTS for Cantonese, which ...
We'd like to use the text to speech service to control an animatronic. The animatronic has a mouth and needs to manipulate its lips and jaws as it's speaking and Amazon had phoneme and viseme support which is what we were using. However, we're swi...
The previous generation German models do not have any upper case words or punctuation. The next generation model (telephony only for now) has no punctuation and almost no correct upper case words. For German, proper case and at least some basic pu...
Remove Limitation of article length in text to speech api
We are using text to speech service to transcode texts using the api. Unfortunately, the api limits the size of text to 5kb. Most of our texts have a size > 5kb. Please remove or adjust the maximum size of texts in order to make longer texts po...
Utterance segmentation made sensitive to speaker identity (features)
Utterance segmentation appears to be entirely independent of (the features used for) speaker labeling. Specifically, it was noticed that even though the speaker labeling correctly identifies that a new speaker (very clear because it goes from mal...
Automatically detect the voice model to improve transcription in use cases where multiple speakers have different accents (e.g. US and UK on the same line) - similar to language detection in Watson Assistant.
Do not place IBM confidential, company confidential, or personal information into any field.