Speech Services

Showing 25

German model needs proper case and punctuation

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...

almost 3 years ago in Speech Services 0

2 VOTE

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...

almost 3 years ago in Speech Services 0 Future consideration

1 VOTE

Watson Speech to Text should return timestamps accurate to milliseconds for transcription

Real-life scenario: Researchers from Brandeis University, Boston University, Harvard, Boston College, and Northeastern University are investigating cognitive aging and biomarkers of dementia. Currently, they have been hand-scoring cognitive interv...

almost 3 years ago in Speech Services 2 Not under consideration

2 VOTE

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 male...

almost 6 years ago in Speech Services 1 Functionality already exists

2 VOTE

Automatic Voice Model detection

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.

over 6 years ago in Speech Services 1 Not under consideration

1 VOTE

Allow metadata to be saved with custom language models

We need to create and manage custom language models for a potentially large number of different clients. We would like to be able to save metadata with a custom language model that would help us to identify things like what client account the cust...

over 3 years ago in Speech Services 0 Planned for future release

1 VOTE

usability of the new IBM Watson tts demo site

When we did the project "spaceships with opinions" the IBM Watson tts-demo site was a great help. So I feel I have a responsibility to tell you how I think the new site is failing. https://www.ibm.com/demos/live/tts-demo/self-service/home It works...

almost 4 years ago in Speech Services 3 Not under consideration

1 VOTE

Help with audio file slicing

Currently I can submit a word or phrase with an audio file and receive back the time code of the word or phrase. We need the time codes of the periods, question marks, and exclamation marks. In other words, we want to upload a transcript with the ...

about 4 years ago in Speech Services 2 Planned for future release

1 VOTE

Add flag to instances to indicate if have customizations

When building a UI for Phone integration -- the reasons to select a particular STT or Voice instance over another are the plan and whether it has customizations available. At this time to, when a user selects a speech instance, you must do several...

over 4 years ago in Speech Services 0 Planned for future release

1 VOTE

Retreive sound file previously streamed to Watson Speech-to-Text

When working on improving our product, we'd like to capture field failures that could be used to train our custom speech-to-text model. We have a wake word (handled locally) and then we establish a connection to IBM Watson's Speech-to-Text service...

about 5 years ago in Speech Services 2 Not under consideration

Please enter your email address

FILTER BY CATEGORY