Questions tagged [speech-synthesis]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
62
votes
11answers
47k views

Is there an online tool to convert IPA symbols into audio sound?

As many amateurs and beginners know, IPA is difficult to memorize and internalize at first. Does software exist where one can paste in IPA text and hear synthesized speech (ideally in the form of a ...
4
votes
1answer
131 views

Where does Google's pronunciation notation come from?

When you search for "X pronunciation" on Google, it shows the "Sounds like x·y·z" box with phonetic respelling. Does anyone know if this respelling system is based on a particular ...
5
votes
3answers
113 views

What is the name of the category that describes the ways a number can be read?

About 6 days ago, I asked this question in the English Language and Usage section but have yet to receive any answer. In hindsight, the lack of answers is entirely understandable since that was not ...
1
vote
2answers
104 views

Is there software (eg. desktop or mobile app) out there that helps learners learn all the sounds of the world with the IPA?

I wished there was one where the app would synthesise a sound for some phoneme X, displaying the IPA symbol at the same time, then ask the user to repeat the sound, which the software checks for the ...
7
votes
1answer
183 views

How to synthesize French vowels

I am trying to synthesize the French vowels [o] and [ɔ] for running a perception experiment. I have been using the Praat Vocal Toolkit and got pretty nice results with the following formant values: F1(...
0
votes
1answer
545 views

Text to Speech Systems for Arabic

In view of the fact that Arabic omits the diacritics for short vowels and the like, does this pose an extra challenge for text to speech systems for the Arabic language? How easy is it to resolve ...
3
votes
0answers
29 views

Are there standards to compare naturalness of synthetic voices?

Say that I wanted to compare Siri and Google Voice in terms of naturalness or similarity to human speech. Obviously I could give a bunch of people a survey and collate their opinions — but I wonder if ...
2
votes
5answers
1k views

Algorithm for figuring out the pronunciation of a word

Wondering how we pronounce words. I feel like I learned this when I was a kid in school with all the language rules, but now I can't remember. I am trying to think about how we pronounce words. How ...
2
votes
1answer
211 views

Text-to-speech for arbitrary vowels (i.e not just ipa)

So my understanding is vowel sounds can be modelled in a 2-d space together with roundedness in terms of location and openness or equivalently in terms of first and second formants. You get pictures ...
2
votes
0answers
231 views

Where do I start if I want to a create a syllable like /ba/ or /pa/?

I want to create some syllable like /ba/, /pa/, /ta/, /da/, with either Praat or Klatt synthesis interface. But I was overwhelmed by the information I found on the Internet. I was wondering what I ...
1
vote
1answer
72 views

Help understanding letter sets

I am trying to understand the working of an old computer speech synthesizer (SAM for the commodore64) which uses a series of rules to break English text into a string of phonemes. The rules make some ...
2
votes
0answers
64 views

Computational production of diphthongs

I am trying to generate vowels on MATLAB by using source-filter model. In case of monophthongs I'm using Rosenberg pulse as my source signal and then this source signal is convoluted with sounds ...
1
vote
1answer
99 views

What kind of speech synthesis is "HMM synthesis"?

The Wikipedia page on synthetic speech claims: The two primary technologies generating synthetic speech waveforms are concatenative synthesis and formant synthesis. It then goes on to describe ...
5
votes
2answers
783 views

Algorithm for Separating Consonant and Vowel Waveforms from Speech Signal

Is anyone aware of a software package or general algorithm that allows the separation of consonant and vowel waveforms from a continuous speech signal? I've tried to implement the technique "Harmonic/...
1
vote
0answers
72 views

Is it possible to force the Google speech synthesis engine to pronounce individual phonemes?

I wish to have an app makes individual sounds of letters (phonemes) and I'm wondering if, rather than record them all myself, I can force Google's speech synthesis engine to give me individual sounds. ...
4
votes
1answer
179 views

Is there a public sound bank of the IPA?

I'm looking for a comprehensive audio database of the IPA, spoken by the same individual. I realize the this restriction may not include the full set of the IPA and I'm willing to settle on the ...
1
vote
2answers
932 views

Core organs of speech

Do you think the core human 'organs' for speech/sound production can be reduced to the lips, tongue and throat? I realize there are elements like nasals and glottal stops but the other three seem to ...
3
votes
2answers
300 views

What are the best online resources for learning about (and making?) synthetic speech?

I was surprised to find so little in iTunesUniversity, though maybe I need different search criteria. Is there any open source resource to make or manipulate synthetic speech?
3
votes
1answer
87 views

How do prosodic models inform improvements to speech synthesis?

How does the state-of-the-art in speech synthesis take into account prosody? It is not clear to me how e.g. Klatt Durational Model, IITM Durational Model, Sums-of-Products Model, or even Neural ...
2
votes
1answer
316 views

What is harder? Speech synthesis or speech recognition?

Supposing to use Festival to build a speech synthesis system and HTK for a speech recognition system. The language is a Native American language. Which system would be harder to accomplish?