Read, Share and forward,

I have been a long-time user of Speech Recognition & Synthesis (formerly
Google Text-to-Speech), having used it across various Android devices
(Android 8 to 14). While it offers multiple voices and language support, I
believe significant improvements are necessary. Since its release on
October 10, 2013, there have not been any major updates. Simply providing
multiple voices in each language is not helpful if the quality is poor.

Areas for Improvement

Voice Quality: The current voices sound weird, unclear, and lack natural
pronunciation. They come across as robotic, which is a major drawback.
Additionally, there is a noticeable mispronunciation of Indian names when
the language is set to English (India), making the experience feel sluggish
and less intuitive.

User Feedback: Despite constant feedback and suggestions from the blind
community, there seems to be a lack of implementation. High-quality online
voices should be directly available with TalkBack to enhance the user
experience.

Low Latency: There is a noticeable delay between typing or using the
smartphone and hearing announcements for characters typed or functions
where the cursor moves. Sometimes, the system announces numbers in a time
format even when it is not necessary. To avoid this, users should have
control over the announcement formats.

Feature Recommendations

Number Reading: When reading content or checking missed calls, it announces
numbers in thousands, millions, and billions, which is inconvenient. Users
should have the option to choose how numbers are read (digits, doubles,
triplets, and pairs). There should also be a dictionary feature so that
users can correct pronunciation as needed.

Symbol and Punctuation Reading Options: Users should be given the option to
choose how symbols and punctuations are read (all, some, most, or none).
This level of customization will improve accessibility for users with
varying preferences.

Addressing Challenges with Multi-language Content

Multi-language Content Handling: Auto-language detection needs improvement
for content containing multiple languages, such as Gujarati, Hindi, and
English. The app should switch to the appropriate voice based on the
language detected in each section of the text. Note: These examples are
indicative; the principle applies to all languages, whether they are
foreign or Indian. The fact that the author and creator of the report is
from Gujarat, India, is the reason for the inclusion of Indian languages as
examples. Enhancements in this area will provide a more natural and
seamless reading experience for users encountering mixed-language content.

Overall Performance

Speed, accuracy, and overall user experience need significant improvement.
Even with the latest version, the app feels ineffective.

Focus on Accessibility through Action

Promoting accessibility through actions speaks louder than words. I urge
Google to take these issues seriously and fix them as soon as possible.
These improvements would benefit the entire blind community.

I do not hope but am quite sure that this helps.

Thanks and Regards,
Yatin Panchal.

-- 
Disclaimer:
1. Contents of the mails, factual, or otherwise, reflect the thinking of the 
person sending the mail and AI in no way relates itself to its veracity;

2. AI cannot be held liable for any commission/omission based on the mails sent 
through this mailing list..


Search for old postings at:
http://www.mail-archive.com/accessindia@accessindia.org.in/
--- 
You received this message because you are subscribed to the Google Groups 
"AccessIndia" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to accessindia+unsubscr...@accessindia.org.in.
To view this discussion on the web visit 
https://groups.google.com/a/accessindia.org.in/d/msgid/accessindia/CALN9kYLCNp7hY5MP%2BT724vOBfG-RxmmaKT8vEhJBO3ymj%3DAqdw%40mail.gmail.com.

Reply via email to